{"slug":"contextosai-harness-audit","source_name":"contextosai/harness-audit","name":"Contextosai/Harness Audit","description":"Audit an AI agent harness for production readiness from repository code, configuration, tests, and run traces. Score 44 runtime controls across eight outcomes with artifact evidence, identify audit limitations, assign an evidenced maturity band, make a launch decision, and produce a dependency- ordered fix queue. Use for agent safety, governance, ship-readiness, control- gap, or due-diligence reviews of LangGraph, OpenAI Agents SDK, Google ADK, CrewAI, multi-agent, MCP-enabled, or custom agent s","version":2,"lift":{"pass_rate_delta_pts":48,"pass_rate_pct":88,"total_cases":25,"passed_cases":22,"tokens_delta_pct":132.9,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-09T17:05:50.554728+00:00"},"skill_score":0.88,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":48,"with_pass_pct":88,"without_pass_pct":40,"tokens_delta_pct":132.9,"turns_delta_pct":0,"total_cases":25,"cases_aggregated":23,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-09T17:05:50.554728+00:00","run_id":"367716aa-146a-466e-ae9a-5e50b2c58868","version_number":2,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"5424462affdab7c9fef7bb465ed839cf4c1e895bbeaadd5c5358fb904cb9f142","raw_url":"https://app.decimal.ai/s/contextosai-harness-audit/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/contextosai-harness-audit"}