{"eval":{"version":"openagentskill-skill-eval-v1","slug":"noya21th-claude-source-leaked","name":"Claude Source Leaked","generated_at":"2026-06-23T23:19:58.306Z","task_input":"Evaluate Claude Source Leaked before installing it in an AI agent workflow","status":"review","score":74,"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},"task_fit":{"score":94,"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Chunk documents","Create embeddings"],"suited_agents":["TypeScript","Developer Tools","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"]},"install":{"command":"npx skills add noya21th/claude-source-leaked","ready":true,"policy":"review","safety_label":"Review before install","targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add noya21th/claude-source-leaked"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Claude Source Leaked\" agent skill from https://github.com/noya21th/claude-source-leaked. 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: Claude Code v2.1.88 source analysis: system prompts, 87 hidden feature flags, cost optimization, architecture diagrams, undercover mode, and comparison with Cursor/Cline. No source code redistributed."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Claude Source Leaked\" as a Claude Code skill from https://github.com/noya21th/claude-source-leaked. 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: Claude Code v2.1.88 source analysis: system prompts, 87 hidden feature flags, cost optimization, architecture diagrams, undercover mode, and comparison with Cursor/Cline. No source code redistributed."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Claude Source Leaked\" from https://github.com/noya21th/claude-source-leaked 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: Claude Code v2.1.88 source analysis: system prompts, 87 hidden feature flags, cost optimization, architecture diagrams, undercover mode, and comparison with Cursor/Cline. No source code redistributed."}]},"trust":{"score":78,"label":"Strong shortlist","version":"trust-score-v4","evidence":{"stars":"122 GitHub stars","repoActivity":"122 stars, 146 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/noya21th/claude-source-leaked","install":"npx skills add noya21th/claude-source-leaked","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"}},"audit":{"score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","License clarity: Unknown"]},"safety_gate":{"score":62,"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","blocked":false,"permission_hints":[{"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":["License is unclear"]},"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 Claude Source Leaked before installing it in an AI agent workflow","coding-agents","Coding agents workflows; Claude Code teams; builders willing to evaluate younger projects"]},{"id":"install_path","label":"Install path","status":"pass","score":92,"required_for_auto_install":true,"detail":"Install handoff is available.","evidence":["npx skills add noya21th/claude-source-leaked"]},{"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 noya21th/claude-source-leaked"]},{"id":"trust_score","label":"Trust score","status":"warn","score":78,"required_for_auto_install":true,"detail":"Good trust signals with a few areas worth checking before rollout.","evidence":["Strong shortlist","122 GitHub stars","Unknown"]},{"id":"audit_score","label":"Audit score","status":"warn","score":78,"required_for_auto_install":true,"detail":"Needs review","evidence":["License is unclear"]},{"id":"agent_safety_gate","label":"Agent safety gate","status":"warn","score":62,"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.","License is unclear"]},{"id":"readme_skillmd_completeness","label":"README/SKILL.md completeness","status":"pass","score":90,"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":"warn","score":42,"required_for_auto_install":true,"detail":"Unknown","evidence":["Unknown"]},{"id":"recent_maintenance","label":"Recent maintenance","status":"pass","score":88,"required_for_auto_install":false,"detail":"3mo since push","evidence":["3mo since push"]},{"id":"permission_surface","label":"Permission surface","status":"pass","score":86,"required_for_auto_install":true,"detail":"filesystem or document access","evidence":["Network access: medium","Filesystem access: medium"]},{"id":"alternatives","label":"Alternatives available","status":"pass","score":82,"required_for_auto_install":false,"detail":"Alternative skills are available for comparison.","evidence":["anomalyco-opencode","puppeteer-puppeteer","openai-codex","hoppscotch-hoppscotch"]}],"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.","License clarity: Unknown","License is unclear","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."],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No major risk signals from current metadata","License is unclear","Quality score needs review","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"alternatives":[{"slug":"anomalyco-opencode","name":"Opencode","url":"https://www.openagentskill.com/skills/anomalyco-opencode","stars":175041,"install_command":"npx skills add anomalyco/opencode","trust_score":93,"audit_score":95},{"slug":"puppeteer-puppeteer","name":"Puppeteer","url":"https://www.openagentskill.com/skills/puppeteer-puppeteer","stars":94783,"install_command":"npx skills add puppeteer/puppeteer","trust_score":92,"audit_score":94},{"slug":"openai-codex","name":"Codex","url":"https://www.openagentskill.com/skills/openai-codex","stars":91367,"install_command":"npx skills add openai/codex","trust_score":90,"audit_score":93},{"slug":"hoppscotch-hoppscotch","name":"Hoppscotch","url":"https://www.openagentskill.com/skills/hoppscotch-hoppscotch","stars":79567,"install_command":"npx skills add hoppscotch/hoppscotch","trust_score":90,"audit_score":93}],"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"noya21th-claude-source-leaked","name":"Claude Source Leaked","description":"Claude Code v2.1.88 source analysis: system prompts, 87 hidden feature flags, cost optimization, architecture diagrams, undercover mode, and comparison with Cursor/Cline. No source code redistributed.","category":"coding-agents","url":"https://www.openagentskill.com/skills/noya21th-claude-source-leaked","repository":"https://github.com/noya21th/claude-source-leaked","github_repo":"noya21th/claude-source-leaked"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Chunk documents","Create embeddings"],"suited_agents":["TypeScript","Developer Tools","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add noya21th/claude-source-leaked","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add noya21th/claude-source-leaked"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Claude Source Leaked\" agent skill from https://github.com/noya21th/claude-source-leaked. 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: Claude Code v2.1.88 source analysis: system prompts, 87 hidden feature flags, cost optimization, architecture diagrams, undercover mode, and comparison with Cursor/Cline. No source code redistributed."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Claude Source Leaked\" as a Claude Code skill from https://github.com/noya21th/claude-source-leaked. 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: Claude Code v2.1.88 source analysis: system prompts, 87 hidden feature flags, cost optimization, architecture diagrams, undercover mode, and comparison with Cursor/Cline. No source code redistributed."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Claude Source Leaked\" from https://github.com/noya21th/claude-source-leaked 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: Claude Code v2.1.88 source analysis: system prompts, 87 hidden feature flags, cost optimization, architecture diagrams, undercover mode, and comparison with Cursor/Cline. No source code redistributed."}],"handoff_url":"https://www.openagentskill.com/api/skills/noya21th-claude-source-leaked/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/noya21th-claude-source-leaked"},"trust":{"score":78,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"122 GitHub stars","repoActivity":"122 stars, 146 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/noya21th/claude-source-leaked","install":"npx skills add noya21th/claude-source-leaked","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"success_rate":null,"install_attempts":0,"risk_blocked":0,"setup_required":0,"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":["coding-agents","developer-tools","automation","coding","ai-agent","ai-coding"],"known_risks":["License is unclear","Quality score needs review","License clarity: Unknown"]},"audit":{"score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","License clarity: Unknown"]},"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":67,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"3mo since push","risk":"Needs review"},"alternative_skills":[{"slug":"anomalyco-opencode","name":"Opencode","url":"https://www.openagentskill.com/skills/anomalyco-opencode","stars":175041,"install_command":"npx skills add anomalyco/opencode","trust_score":93,"audit_score":95},{"slug":"puppeteer-puppeteer","name":"Puppeteer","url":"https://www.openagentskill.com/skills/puppeteer-puppeteer","stars":94783,"install_command":"npx skills add puppeteer/puppeteer","trust_score":92,"audit_score":94},{"slug":"openai-codex","name":"Codex","url":"https://www.openagentskill.com/skills/openai-codex","stars":91367,"install_command":"npx skills add openai/codex","trust_score":90,"audit_score":93},{"slug":"hoppscotch-hoppscotch","name":"Hoppscotch","url":"https://www.openagentskill.com/skills/hoppscotch-hoppscotch","stars":79567,"install_command":"npx skills add hoppscotch/hoppscotch","trust_score":90,"audit_score":93}],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No major risk signals from current metadata","License is unclear","Quality score needs review","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Evaluate Claude Source Leaked before installing it in an AI agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 78/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"noya21th-claude-source-leaked (Claude Source Leaked)","install_command":"npx skills add noya21th/claude-source-leaked","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."}},"endpoints":{"web":"https://www.openagentskill.com/skills/noya21th-claude-source-leaked","api":"https://www.openagentskill.com/api/agent/skills/noya21th-claude-source-leaked","audit":"https://www.openagentskill.com/skills/noya21th-claude-source-leaked/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=noya21th-claude-source-leaked&task=Evaluate%20Claude%20Source%20Leaked%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20Claude%20Source%20Leaked%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium","install":"https://www.openagentskill.com/api/skills/noya21th-claude-source-leaked/install","manifest":"https://www.openagentskill.com/api/registry/manifest/noya21th-claude-source-leaked"}},"endpoints":{"web":"https://www.openagentskill.com/skills/noya21th-claude-source-leaked","api":"https://www.openagentskill.com/api/agent/skills/noya21th-claude-source-leaked","eval":"https://www.openagentskill.com/api/agent/evals?slug=noya21th-claude-source-leaked","audit":"https://www.openagentskill.com/skills/noya21th-claude-source-leaked/audit","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20Claude%20Source%20Leaked%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium"}},"meta":{"endpoint":"/api/agent/evals","mode":"skill_eval","purpose":"Pre-install eval contract for a single skill. Agents should read this before installing a reusable skill.","generated_at":"2026-06-23T23:19:58.306Z"}}