Individual skill
agent-harness
Test and evaluation harness for AI agents — scenario suites, deterministic replay, regression diffing, cost and latency budgets. Use when agent quality is vibe-checked, before shipping a prompt or model change, or when evals drift.
engineering/agent-harness/SKILL.md
Source commit 25bf86b89c6c1e63f433a5b65e8cfcb6cf0b7ad3
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 10, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 1,099
- Repository last updated
- Nov 8, 2026
- License
- NOASSERTION
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-agents Repository topic
- ai-skills Repository topic
- claude-code Repository topic
- developer-tools Repository topic
- agentic-coding Repository topic
- cursor Repository topic
- github-copilot Repository topic
- compliance-automation Repository topic
- claude-skills Repository topic
- gemini-cli Repository topic
- agent-eval Declared skill tag
- regression-testing Declared skill tag
- harness Declared skill tag
- replay Declared skill tag
- llm-testing Declared skill tag
- testing Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 14,781 bytesSKILL.mdcore · 14,781 bytesSKILL.mdcore · 14,781 bytesSKILL.mdcore · 14,781 bytesassets/eval_report_template.mddoc · 2,045 bytesassets/sample_baseline_report.jsonasset · 8,072 bytesassets/sample_candidate_report.jsonasset · 8,065 bytesassets/sample_suite.jsonasset · 3,232 bytesassets/sample_transcripts_baseline.jsonasset · 3,055 bytesassets/sample_transcripts_candidate.jsonasset · 2,892 bytesassets/scenario_authoring_checklist.mddoc · 2,422 bytesreferences/eval-methodology-and-budgets.mddoc · 9,688 bytesreferences/scenario-and-fixture-design.mddoc · 10,030 bytesscripts/eval_diff.pyruns · 10,272 bytesscripts/scenario_runner.pyruns · 11,539 bytes
No licensed excerpt is available. You can inspect the pinned source.