{"version":"openagentskill-agent-integration-kit-v2","connection_modes":{"session":"Default. Use the API in this conversation without saving configuration or installing anything.","persistent":"Optional, only with explicit user approval. Add the remote HTTP MCP endpoint through the client supported settings, preserve existing servers, reload, then test tools in that client."},"self_check":{"script_url":"https://www.openagentskill.com/connect-check.mjs","requirements":"A network-capable agent with HTTP tools, or Node.js 18+ to run the inspected dependency-free script.","command":"node connect-check.mjs","instructions":"Download and inspect the script before authorizing execution. It reads public registry data only; it does not save configuration, install Skills, call a model API, or report installation outcomes.","expected_checks":["api_accessible","tools_available","search_working"],"configuration_saved":"not_verified","client_verification":"After any approved persistent setup, use the actual client MCP tool list and search_skills with query mono-color. A standalone script passing does not verify native client configuration.","failure_action":"Report the failed stage and error. Do not claim connected, bypass safety checks, or install a Skill to make the test pass."},"purpose":"Let an AI agent resolve a task into the right reusable skill, compare alternatives, review trust signals, and install with a safe handoff.","canonical_page":"https://www.openagentskill.com/agent/integration-kit","api":"https://www.openagentskill.com/api/agent/integration-kit","resolve_api":"https://www.openagentskill.com/api/agent/resolve","receipt_api":"https://www.openagentskill.com/api/agent/receipt","outcome_api":"https://www.openagentskill.com/api/agent/outcome","mcp":"https://www.openagentskill.com/api/mcp","sdk":"@openagentskill/sdk","manifest":"https://www.openagentskill.com/.well-known/agent-manifest.json","llms":"https://www.openagentskill.com/llms.txt","supported_agents":[{"id":"codex","name":"Codex","surface":"Coding agent / local workspace","best_for":["repo-aware implementation","code review","debugging","web automation setup"],"setup_steps":["Paste the copy prompt into this conversation first. Save project instructions or MCP settings only after explicit user approval.","Call the Resolve API with the current task and agent=codex.","Read agent_handoff.review_checklist before installing a third-party skill.","Install only in the active workspace after reporting files and commands that will be touched."],"default_task":"scrape pricing pages and extract structured data","resolve_url":"https://www.openagentskill.com/api/agent/resolve?task=scrape%20pricing%20pages%20and%20extract%20structured%20data&agent=codex&max_risk=medium","receipt_url":"https://www.openagentskill.com/api/agent/receipt?task=scrape%20pricing%20pages%20and%20extract%20structured%20data&agent=codex&max_risk=medium&format=text","copy_prompt":"You are using OpenAgentSkill as the skill resolution layer for Codex.\nDefault to this conversation only: do not change project instructions, global configuration, or install packages.\nRead https://www.openagentskill.com/connect-check.mjs and, if Node.js 18+ is available and execution is authorized, run the inspected read-only check. Alternatively perform its documented HTTP/MCP requests with your existing tools.\nReport API accessibility, MCP tool availability, and search success separately. Configuration saved remains not_verified unless you actually saved and reloaded the client configuration with user approval.\nFor persistent MCP setup, request approval first, add https://www.openagentskill.com/api/mcp using the client supported remote HTTP MCP settings, preserve all existing servers, and verify native tool listing and one read-only search after reloading.\nIf this client cannot access the network or call tools, explain that limitation; do not claim connected.\nNever transmit private task text, source code, credentials or environment values. Use a public, sanitized task description only.\nBefore building a custom workflow from scratch, call the Resolve API with the user task.\nIf selected is null or policy_decision reports no_match, explain that no eligible Skill was found. review_candidates are research leads, not installation recommendations; never invent an install command or approval for them.\nResolve endpoint: https://www.openagentskill.com/api/agent/resolve?task={USER_TASK}&agent=codex&max_risk=medium\nInstall receipt endpoint: https://www.openagentskill.com/api/agent/receipt?task={USER_TASK}&agent=codex&max_risk=medium&format=text\nUse install_receipt as the stable pre-install record only after checking risk, safety_gate, and agent_handoff.review_checklist.\nIf auto_install_allowed is false, ask for human approval before installing.\nIf blocked is true or risk notes mention secrets, shell, token, or network risk, do not auto-install.\nAfter one narrow run, POST the result to install_receipt.outcome_feedback.endpoint with install_receipt.outcome_feedback.event_id so future rankings learn from real outcomes.\nReturn the selected skill, install command, receipt id, alternatives, risk summary, outcome event id, and next action before changing files.","expected_output_contract":["selected_skill","install_command","risk_summary","outcome_event_id","alternatives","files_or_commands_to_touch","next_action"]},{"id":"claude-code","name":"Claude Code","surface":"Claude Code skill workflow","best_for":["local skill instructions","project workflows","documentation-heavy tasks"],"setup_steps":["Paste the copy prompt at the start of a task. Persistent custom instructions or MCP setup require explicit user approval.","Call the Resolve API with agent=claude-code.","Use install targets only after audit and eval checks are acceptable.","Keep the skill scoped to the project and summarize activation steps."],"default_task":"scrape pricing pages and extract structured data","resolve_url":"https://www.openagentskill.com/api/agent/resolve?task=scrape%20pricing%20pages%20and%20extract%20structured%20data&agent=claude-code&max_risk=medium","receipt_url":"https://www.openagentskill.com/api/agent/receipt?task=scrape%20pricing%20pages%20and%20extract%20structured%20data&agent=claude-code&max_risk=medium&format=text","copy_prompt":"You are using OpenAgentSkill as the skill resolution layer for Claude Code.\nDefault to this conversation only: do not change project instructions, global configuration, or install packages.\nRead https://www.openagentskill.com/connect-check.mjs and, if Node.js 18+ is available and execution is authorized, run the inspected read-only check. Alternatively perform its documented HTTP/MCP requests with your existing tools.\nReport API accessibility, MCP tool availability, and search success separately. Configuration saved remains not_verified unless you actually saved and reloaded the client configuration with user approval.\nFor persistent MCP setup, request approval first, add https://www.openagentskill.com/api/mcp using the client supported remote HTTP MCP settings, preserve all existing servers, and verify native tool listing and one read-only search after reloading.\nIf this client cannot access the network or call tools, explain that limitation; do not claim connected.\nNever transmit private task text, source code, credentials or environment values. Use a public, sanitized task description only.\nBefore building a custom workflow from scratch, call the Resolve API with the user task.\nIf selected is null or policy_decision reports no_match, explain that no eligible Skill was found. review_candidates are research leads, not installation recommendations; never invent an install command or approval for them.\nResolve endpoint: https://www.openagentskill.com/api/agent/resolve?task={USER_TASK}&agent=claude-code&max_risk=medium\nInstall receipt endpoint: https://www.openagentskill.com/api/agent/receipt?task={USER_TASK}&agent=claude-code&max_risk=medium&format=text\nUse install_receipt as the stable pre-install record only after checking risk, safety_gate, and agent_handoff.review_checklist.\nIf auto_install_allowed is false, ask for human approval before installing.\nIf blocked is true or risk notes mention secrets, shell, token, or network risk, do not auto-install.\nAfter one narrow run, POST the result to install_receipt.outcome_feedback.endpoint with install_receipt.outcome_feedback.event_id so future rankings learn from real outcomes.\nReturn the selected skill, install command, receipt id, alternatives, risk summary, outcome event id, and next action before changing files.","expected_output_contract":["selected_skill","skill_files_or_instructions","install_prompt","risk_summary","outcome_event_id","activation_steps","fallback_skill"]},{"id":"cursor","name":"Cursor","surface":"Cursor rules / agent instructions","best_for":["project rules","repeatable coding workflows","IDE assistant guidance"],"setup_steps":["Paste the copy prompt into agent chat. Persistent rules or MCP settings require explicit user approval.","Call the Resolve API with agent=cursor.","Turn the selected skill into a narrow project rule only when the safety gate allows it.","Keep generated rules task-scoped and avoid broad always-on instructions."],"default_task":"scrape pricing pages and extract structured data","resolve_url":"https://www.openagentskill.com/api/agent/resolve?task=scrape%20pricing%20pages%20and%20extract%20structured%20data&agent=cursor&max_risk=medium","receipt_url":"https://www.openagentskill.com/api/agent/receipt?task=scrape%20pricing%20pages%20and%20extract%20structured%20data&agent=cursor&max_risk=medium&format=text","copy_prompt":"You are using OpenAgentSkill as the skill resolution layer for Cursor.\nDefault to this conversation only: do not change project instructions, global configuration, or install packages.\nRead https://www.openagentskill.com/connect-check.mjs and, if Node.js 18+ is available and execution is authorized, run the inspected read-only check. Alternatively perform its documented HTTP/MCP requests with your existing tools.\nReport API accessibility, MCP tool availability, and search success separately. Configuration saved remains not_verified unless you actually saved and reloaded the client configuration with user approval.\nFor persistent MCP setup, request approval first, add https://www.openagentskill.com/api/mcp using the client supported remote HTTP MCP settings, preserve all existing servers, and verify native tool listing and one read-only search after reloading.\nIf this client cannot access the network or call tools, explain that limitation; do not claim connected.\nNever transmit private task text, source code, credentials or environment values. Use a public, sanitized task description only.\nBefore building a custom workflow from scratch, call the Resolve API with the user task.\nIf selected is null or policy_decision reports no_match, explain that no eligible Skill was found. review_candidates are research leads, not installation recommendations; never invent an install command or approval for them.\nResolve endpoint: https://www.openagentskill.com/api/agent/resolve?task={USER_TASK}&agent=cursor&max_risk=medium\nInstall receipt endpoint: https://www.openagentskill.com/api/agent/receipt?task={USER_TASK}&agent=cursor&max_risk=medium&format=text\nUse install_receipt as the stable pre-install record only after checking risk, safety_gate, and agent_handoff.review_checklist.\nIf auto_install_allowed is false, ask for human approval before installing.\nIf blocked is true or risk notes mention secrets, shell, token, or network risk, do not auto-install.\nAfter one narrow run, POST the result to install_receipt.outcome_feedback.endpoint with install_receipt.outcome_feedback.event_id so future rankings learn from real outcomes.\nReturn the selected skill, install command, receipt id, alternatives, risk summary, outcome event id, and next action before changing files.","expected_output_contract":["selected_skill","cursor_rule_or_prompt","install_command","risk_summary","outcome_event_id","when_to_use","when_not_to_use"]}],"recommended_flow":["Read /llms.txt or /.well-known/agent-manifest.json.","Default to session-only HTTP calls. Configure /api/mcp for native tool calls only with explicit user approval.","Choose the Codex, Claude Code, or Cursor template for the active agent surface.","Call /api/agent/resolve with task, agent, max_risk, and optional min_stars.","Read install_receipt, recommendation.best_skill, recommendation.install, recommendation.risk, and agent_handoff.","Fetch /api/agent/receipt?task=...&agent=...&format=text when a compact pre-install execution record is easier for the agent runtime.","If auto_install_allowed is false, ask for human approval before installing.","Fetch /api/agent/evals and /api/agent/skills/{slug} before production use.","Install in a sandbox or low-risk workspace first.","Report success, failed, not_relevant, blocked_by_risk, or setup_required to /api/agent/outcome with output_quality, workspace, and error_type when available."],"stable_response_fields":["feedback.event_id","feedback.outcome_api","feedback.cli_example","install_receipt.receipt_id","install_receipt.selected_skill","install_receipt.install","install_receipt.risk","install_receipt.outcome_feedback","agent_feedback_loop","recommendation.best_skill","recommendation.install","recommendation.why_recommended","recommendation.risk","recommendation.alternatives","recommendation_lanes.best_match","recommendation_lanes.safer_alternative","recommendation_lanes.popular_alternative","recommendation_lanes.new_contender","recommendation_lanes.no_skill_option","agent_handoff.platform_templates","agent_handoff.review_checklist","agent_handoff.api_sequence","policy_decision","review_candidates"],"safety_rules":["Do not auto-install when safety_gate.blocked is true.","Do not auto-install when recommendation.install.auto_install_allowed is false.","Escalate for human approval when shell, env, token, network, license, or unclear maintenance risk appears.","Prefer a lower-risk alternative when the selected skill has high risk notes."]}