{"slug":"alirezarezvani-agent-harness","name":"agent-harness","description":"Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).","long_description":"---\nname: agent-harness\ndescription: \"Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).\"\n---\n\n# Agent Harness\n\nYou are a harness operator, not a hero. The loop — not your optimism — decides when work\nis done. Your job: compile the goal into tasks with checks, execute one task at a time,\nlet the controller adjudicate verification, and stop when the state machine says stop.\n\n## The contract\n\n```\nGOAL → goal_compiler → PLAN → loop_controller: [execute → verify]* → CLOSE\n                                     ↑______retry (≤ max_attempts, changed approach)\n                                     └── ESCALATE on exhausted budgets — never fake success\n```\n\nThree layers, all JSON: a committed per-domain **manifest** (what skills/tools/checks\nexist), a per-goal **plan** (which tasks, which verifications, what \"done\" means), and a\nper-run **state file** (the single source of truth; a fresh session resumes from it alone).\n\n## Quick start\n\n```bash\n# 0. Pick the domain manifest (18 committed under assets/harnesses/, e.g. engineering-team.json)\nls assets/harnesses/\n\n# 1. Compile the goal (refuses vague goals with exit 3 + forcing questions)\npython3 scripts/goal_compiler.py \\\n  --goal \"audit the payments service and design an SLO with an error budget\" \\\n  --manifest assets/harnesses/engineering.json --out plan.json\n\n# 2. Initialize the loop state\npython3 scripts/loop_controller.py init --plan plan.json --state .agent-harness/state.json\n\n# 3. Drive the loop — repeat until directive is \"close\" or \"escalate\"\npython3 scripts/loop_controller.py next --state .agent-harness/state.json\n#    → {\"action\": \"execute\", \"task\": \"T1\", ...}: open the task's skill (SKILL.md at\n#      skill_path), do the work with its tools, then:\npython3 scripts/loop_controller.py record --state .agent-harness/state.json \\\n  --task T1 --phase execute --exit-code 0\n#    → the controller runs the task's checks ITSELF (subprocess, timeout, evidence log):\npython3 scripts/loop_controller.py verify --state .agent-harness/state.json --task T1 --cwd <repo-root>\n\n# 4. Close — refused (exit 4) while any task is unverified and unwaived\npython3 scripts/loop_controller.py close --state .agent-harness/state.json\n```\n\nRegenerate a manifest after skills change (diff-stable, CI-checkable):\n\n```bash\npython3 scripts/harness_manifest_builder.py --domain engineering-team \\\n  --repo-root <repo-root> --out-dir assets/harnesses --no-timestamp\n```\n\n## Hard rules\n\n1. **Never adjudicate your own verification.** `verify` runs the checks via subprocess;\n   a passing `record --phase verify` without `--evidence` is rejected (exit 6). You do not\n   get to declare a task verified.\n2. **Never modify a gate you are judged by.** Check commands come from the manifest/plan.\n   Editing a check to make it pass is the reward-hacking failure mode\n   (see [references/verification_discipline.md](references/verification_discipline.md)) — same\n   invariant as autoresearch-agent's locked evaluator.\n3. **One task at a time, writes serialized.** Parallelize reading and judging, never two\n   tasks writing the same artifact ([references/agentic_loop_canon.md](references/agentic_loop_canon.md)).\n4. **Retry means a changed approach.** Same command + same input = same failure. The retry\n   directive says so; honor it.\n5. **Budgets are terminal states, not suggestions.** `max_attempts_per_task` → escalated\n   (exit 2); `max_loop_iterations` → escalate (exit 5). Exhausted budgets are never\n   reported as success — a human waives (`close --waive T3 --reason \"...\"`), you don't.\n6. **Fresh context beats long context.** Every `next` directive is executable by a new\n   session reading only the plan + state files. Long-running goals: run each iteration as\n   its own session against the durable state.\n7. **State lives in `.agent-harness/`** — never in `.agenthub/`, `.autoresearch/`, or\n   `docs/TC/` (those belong to sibling skills).\n8. **Plan and state files are a trust boundary.** `verify` shell-executes each task's\n   check command; only run the harness on plan/state files you or `goal_compiler.py`\n   produced, never on files from untrusted input (see\n   [references/verification_discipline.md](references/verification_discipline.md)).\n\n## Forcing questions (ask before compiling; one per turn, with a recommended answer)\n\n| # | Question | Recommended answer | Why (canon) |\n|---|---|---|---|\n| 1 | What single observable outcome means DONE? | A named artifact + a command that exits 0 against it | Verifier's law: invest in verifiability first |\n| 2 | Which domain harness applies? | The domain whose skills name the deliverable; if two, run two sequential loops | Orchestrator-workers: scoped objectives beat mega-goals |\n| 3 | What must NOT change? | List no-touch paths; put them in the goal text so the compiler's plan inherits them | Boundaries are part of a subagent spec |\n| 4 | Who reviews escalations, and how fast? | A named human; escalations block the loop by design | Approval-required is a terminal state, not a nuisance |\n| 5 | What is the iteration budget? | Default 12 loop iterations / 3 attempts per task; raise only with a reason | Caps are runtime errors, not advice (OpenAI SDK `max_turns`) |\n\n## Exit codes (branch on these mechanically)\n\n| Code | Tool | Meaning |\n|---|---|---|\n| 0 | all | OK / directive emitted |\n| 2 | loop_controller | Escalation required — a human must review the evidence log |\n| 3 | goal_compiler | Goal too vague — answer the forcing questions, recompile |\n| 4 | goal_compiler / loop_controller | No skill matched / close refused (unverified tasks) |\n| 5 | loop_controller | Global iteration cap reached |\n| 6 | loop_controller | Invalid transition (recording on verified task, evidence missing, unknown task) |\n\n## Verifiable success\n\n- `python3 scripts/harness_manifest_builder.py --sample`, `scripts/goal_compiler.py --sample`,\n  and `scripts/loop_controller.py --sample` all exit 0.\n- A vague goal (`--goal \"make it better\"`) exits 3 and prints forcing questions.\n- `loop_controller.py close` on a state with an unverified task exits 4.\n- The demo loop in `loop_controller.py --sample` shows a verify failure consuming an attempt\n  and the loop still closing only after a passing verify with evidence.\n\n## Related skills\n\n- **workflow-builder**: authoring deterministic `.js` scripts for Claude Code's Workflow\n  tool. NOT for goal-to-close loop state (this skill).\n- **agenthub**: N parallel agents competing on ONE task in git worktrees. Use it *inside* a\n  harness task that wants competing attempts.\n- **autoresearch-agent**: metric optimization of a single file against a locked evaluator.\n  Use it when a task's done_when is \"metric improves\".\n- **tc-tracker**: per-code-change lifecycle records. Use for change bookkeeping; the harness\n  state file is per-goal, not per-change.\n- **loop-library**: discover/audit published loop recipes conversationally. This skill is the\n  executable enforcement of that vocabulary.\n- **ship-gate / self-eval / spec-driven-workflow**: plug in as close-time checks inside a\n  task's `verification[]`.\n\nSee [references/domain_harness_design.md](references/domain_harness_design.md) for the\nthree-layer architecture, the reuse map, and how to raise a domain's harness quality.\n","tagline":"Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until eve","category":"research","tags":["agent-skill"],"author":"alirezarezvani","verified":false,"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"recursive skill source sync","sourceDetail":"alirezarezvani/claude-skills","creatorName":"alirezarezvani","creatorUrl":"https://github.com/alirezarezvani","sourceUrl":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/alirezarezvani-agent-harness#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":24795,"forks":3494,"verified_installs":0,"successful_runs":0,"total_outcomes":0,"rating":0,"review_count":0,"quality_score":54.31},"quality":{"score":91,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"25K","tone":"positive"},{"label":"Freshness","value":"Today","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently."]},"trust":{"version":"trust-score-v5","score":73,"base_score":81,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["73/100 Trust Score v5","81/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"25K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"25K stars, 3.5K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"Pushed today"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":86,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add alirezarezvani/claude-skills --skill agent-harness"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":62,"weight":0.07,"status":"info","detail":"shell or command execution, filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"25K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"25K stars, 3.5K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"Pushed today"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add alirezarezvani/claude-skills --skill agent-harness"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution, filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"25K GitHub stars","repoActivity":"25K stars, 3.5K forks","lastPushed":"Pushed today","license":"MIT","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness","install":"npx skills add alirezarezvani/claude-skills --skill agent-harness","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","Pushed today","Financial domain: human review is required before use in a live investment workflow.","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v3","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","trust_score":73,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"knownRisks":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":81,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"trust_score_v5":{"version":"trust-score-v5","score":73,"base_score":81,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["73/100 Trust Score v5","81/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"25K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"25K stars, 3.5K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"Pushed today"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":86,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add alirezarezvani/claude-skills --skill agent-harness"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":62,"weight":0.07,"status":"info","detail":"shell or command execution, filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"25K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"25K stars, 3.5K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"Pushed today"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add alirezarezvani/claude-skills --skill agent-harness"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution, filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"25K GitHub stars","repoActivity":"25K stars, 3.5K forks","lastPushed":"Pushed today","license":"MIT","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness","install":"npx skills add alirezarezvani/claude-skills --skill agent-harness","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","Pushed today","Financial domain: human review is required before use in a live investment workflow.","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v3","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","trust_score":73,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"knownRisks":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":81,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"trust_score_v4":{"version":"trust-score-v4","score":81,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"25K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"25K stars, 3.5K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"Pushed today"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":86,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add alirezarezvani/claude-skills --skill agent-harness"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":62,"weight":0.07,"status":"info","detail":"shell or command execution, filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"25K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"25K stars, 3.5K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"Pushed today"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add alirezarezvani/claude-skills --skill agent-harness"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution, filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"],"evidence":{"stars":"25K GitHub stars","repoActivity":"25K stars, 3.5K forks","lastPushed":"Pushed today","license":"MIT","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness","install":"npx skills add alirezarezvani/claude-skills --skill agent-harness","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","Pushed today","Financial domain: human review is required before use in a live investment workflow."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"knownRisks":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"outcome_stats":null,"safety":{"score":59,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["High-risk permission hints: Shell or command execution","59/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["High-risk permission hints: Shell or command execution","Financial research output is not financial advice; require human review before any live investment decision"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"blocked":false,"human_review_required":true,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["High-risk permission hints: Shell or command execution","59/100 agent safety score"]},"eval":{"version":"openagentskill-skill-eval-v1","status":"review","score":81,"risk_level":"medium","decision":{"recommendation":"manual_review","reason":"Require human approval before installing into a real workspace.","auto_install_allowed":false,"policy":"review","human_review_required":true},"blockers":[],"warnings":["Trust score: Good trust signals with a few areas worth checking before rollout.","Audit score: Needs review","Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.","Permission surface: shell or command execution, filesystem or document access","High-risk permission hints: Shell or command execution","Financial research output is not financial advice; require human review before any live investment decision","The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"],"validation_plan":["Inspect repository, README/SKILL.md, license, and recent commits before production use.","Install in an isolated workspace or sandbox with no production secrets available.","Run the smallest representative task and record files touched, commands run, network access, and outputs.","Compare the selected skill against at least one alternative when the eval status is review or failed.","Promote only after the agent reports a successful verification result and unresolved warnings are accepted."],"checks":[{"id":"task_fit","label":"Task fit","status":"pass","score":94,"required_for_auto_install":true,"detail":"Task wording matches this skill metadata.","evidence":["Evaluate agent-harness before installing it in an agent workflow","research","Research agents workflows; Claude Code teams; teams that value GitHub adoption signals"]},{"id":"install_path","label":"Install path","status":"pass","score":92,"required_for_auto_install":true,"detail":"Install handoff is available.","evidence":["npx skills add alirezarezvani/claude-skills --skill agent-harness"]},{"id":"install_safety","label":"Install command safety","status":"pass","score":92,"required_for_auto_install":true,"detail":"standard package or runtime install path","evidence":["npx skills add alirezarezvani/claude-skills --skill agent-harness"]},{"id":"trust_score","label":"Trust score","status":"warn","score":81,"required_for_auto_install":true,"detail":"Good trust signals with a few areas worth checking before rollout.","evidence":["Strong shortlist","25K GitHub stars","MIT"]},{"id":"audit_score","label":"Audit score","status":"warn","score":87,"required_for_auto_install":true,"detail":"Needs review","evidence":["Financial research output is not financial advice; require human review before any live investment decision"]},{"id":"agent_safety_gate","label":"Agent safety gate","status":"warn","score":59,"required_for_auto_install":true,"detail":"Usable candidate, but the agent should surface permission and audit notes before installation.","evidence":["Require human approval before installing into a real workspace.","High-risk permission hints: Shell or command execution"]},{"id":"readme_skillmd_completeness","label":"README/SKILL.md completeness","status":"pass","score":86,"required_for_auto_install":false,"detail":"Metadata includes enough usage and workflow context","evidence":["Strong README/SKILL.md context"]},{"id":"license_clarity","label":"License clarity","status":"pass","score":86,"required_for_auto_install":true,"detail":"MIT","evidence":["MIT"]},{"id":"recent_maintenance","label":"Recent maintenance","status":"pass","score":100,"required_for_auto_install":false,"detail":"Pushed today","evidence":["Pushed today"]},{"id":"permission_surface","label":"Permission surface","status":"warn","score":62,"required_for_auto_install":true,"detail":"shell or command execution, filesystem or document access","evidence":["Shell or command execution: high","Network access: medium","Filesystem access: medium"]},{"id":"alternatives","label":"Alternatives available","status":"info","score":55,"required_for_auto_install":false,"detail":"No close alternatives were found in the current shortlist.","evidence":[]}],"endpoints":{"web":"https://www.openagentskill.com/skills/alirezarezvani-agent-harness/evals","api":"/api/agent/evals?slug=alirezarezvani-agent-harness","text":"/api/agent/evals?slug=alirezarezvani-agent-harness&format=text"}},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"alirezarezvani-agent-harness","name":"agent-harness","description":"Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).","category":"research","url":"https://www.openagentskill.com/skills/alirezarezvani-agent-harness","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness","github_repo":"alirezarezvani/claude-skills"},"suited_tasks":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Move data between tools","Transform files"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install alirezarezvani-agent-harness"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"agent-harness\" agent skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"agent-harness\" as a Claude Code skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"agent-harness\" from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/alirezarezvani-agent-harness/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/alirezarezvani-agent-harness"},"trust":{"score":81,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"25K GitHub stars","repoActivity":"25K stars, 3.5K forks","lastPushed":"Pushed today","license":"MIT","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness","install":"npx skills add alirezarezvani/claude-skills --skill agent-harness","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":87,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Financial research output is not financial advice; require human review before any live investment decision","The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":91,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"Pushed today","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"],"agent_contract":{"task_input":"Use agent-harness in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 81/100 Strong shortlist","Audit: 87/100 Needs review","Safety: 59/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"alirezarezvani-agent-harness (agent-harness)","install_command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"alirezarezvani-agent-harness","task":"Use agent-harness in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/alirezarezvani-agent-harness","api":"https://www.openagentskill.com/api/agent/skills/alirezarezvani-agent-harness","audit":"https://www.openagentskill.com/skills/alirezarezvani-agent-harness/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=alirezarezvani-agent-harness&task=Use%20agent-harness%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20agent-harness%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20agent-harness%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/alirezarezvani-agent-harness/install","manifest":"https://www.openagentskill.com/api/registry/manifest/alirezarezvani-agent-harness"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"alirezarezvani-agent-harness","name":"agent-harness","description":"Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).","category":"research","url":"https://www.openagentskill.com/skills/alirezarezvani-agent-harness","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness","github_repo":"alirezarezvani/claude-skills"},"suited_tasks":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Move data between tools","Transform files"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install alirezarezvani-agent-harness"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"agent-harness\" agent skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"agent-harness\" as a Claude Code skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"agent-harness\" from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/alirezarezvani-agent-harness/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/alirezarezvani-agent-harness"},"trust":{"score":81,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"25K GitHub stars","repoActivity":"25K stars, 3.5K forks","lastPushed":"Pushed today","license":"MIT","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness","install":"npx skills add alirezarezvani/claude-skills --skill agent-harness","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":87,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Financial research output is not financial advice; require human review before any live investment decision","The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":91,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"Pushed today","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"],"agent_contract":{"task_input":"Use agent-harness in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 81/100 Strong shortlist","Audit: 87/100 Needs review","Safety: 59/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"alirezarezvani-agent-harness (agent-harness)","install_command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"alirezarezvani-agent-harness","task":"Use agent-harness in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/alirezarezvani-agent-harness","api":"https://www.openagentskill.com/api/agent/skills/alirezarezvani-agent-harness","audit":"https://www.openagentskill.com/skills/alirezarezvani-agent-harness/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=alirezarezvani-agent-harness&task=Use%20agent-harness%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20agent-harness%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20agent-harness%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/alirezarezvani-agent-harness/install","manifest":"https://www.openagentskill.com/api/registry/manifest/alirezarezvani-agent-harness"}},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"github-automation","title":"GitHub automation"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":24795,"starsLabel":"25K","forks":3494,"license":"MIT","qualityScore":91,"trustScore":81,"auditScore":87},"maintenance":{"status":"fresh","label":"Pushed today","daysSincePush":0,"lastPushedAt":"2026-08-22T12:31:34+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Financial research output is not financial advice; require human review before any live investment decision","The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","Needs review"]},"coverageTags":["Research","Research agents","agent-skill"]},"audit":{"audit_score":87,"risk_level":"needs_review","risk_label":"Needs review","quality_score":91,"trust_score":81,"maintenance_score":100,"security_score":78,"install_score":92,"warnings":["Financial research output is not financial advice; require human review before any live investment decision","The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review"]},"quality_signals":{"model":"v2","star_score":30.76,"usage_score":0,"review_score":5.55,"metadata_score":3,"freshness_score":15},"platforms":["Claude Code","OpenAI Agents"],"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"}],"stacks":[{"slug":"research-report-agent","title":"Research report agent","url":"https://www.openagentskill.com/collections/research-report-agent"},{"slug":"content-growth-agent","title":"Content growth agent","url":"https://www.openagentskill.com/collections/content-growth-agent"},{"slug":"coding-review-agent","title":"Coding review agent","url":"https://www.openagentskill.com/collections/coding-review-agent"}],"install":"npx skills add alirezarezvani/claude-skills --skill agent-harness","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install alirezarezvani-agent-harness","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"agent-harness\" agent skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"agent-harness\" as a Claude Code skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"agent-harness\" from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness","github_repo":"alirezarezvani/claude-skills","version":"1.0.0","license":"MIT","urls":{"web":"https://www.openagentskill.com/skills/alirezarezvani-agent-harness","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness","api":"/api/agent/skills/alirezarezvani-agent-harness","install_api":"/api/skills/alirezarezvani-agent-harness/install"},"meta":{"created_at":"2026-08-22T13:22:51.977696+00:00","updated_at":"2026-08-22T13:22:51.977696+00:00","agent_friendly":true}}