Individual skill
agent-harness
Use when an agent should drive a goal in one of this repo's domains to a verified close, before starting the work. Compiles the goal into a task plan with goal_compiler.py and runs it through loop_controller.py, which verifies each task, caps retries and escalates.
engineering/agent-harness/skills/agent-harness/SKILL.md
Source commit 8f082544116fc0d014188e521ca40304cdfc86b0
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)
- 29,631
- Repository last updated
- Nov 11, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agentic-ai Repository topic
- anthropic-claude Repository topic
- claude-ai Repository topic
- claude-code Repository topic
- claude-skills Repository topic
- claude-code-skills Repository topic
- ai-coding-agent Repository topic
- claude-code-plugins Repository topic
- developer-tools Repository topic
- openai-codex Repository topic
- engineering 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 · 7,496 bytesSKILL.mdcore · 7,496 bytesSKILL.mdcore · 7,496 bytesSKILL.mdcore · 7,496 bytesassets/harness_manifest.schema.jsonasset · 3,126 bytesassets/harnesses/agent-launcher.jsonasset · 14,765 bytesassets/harnesses/business-growth.jsonasset · 7,736 bytesassets/harnesses/business-operations.jsonasset · 16,550 bytesassets/harnesses/c-level-advisor.jsonasset · 57,942 bytesassets/harnesses/c-level-agents.jsonasset · 10,772 bytesassets/harnesses/commercial.jsonasset · 18,657 bytesassets/harnesses/compliance-os.jsonasset · 6,540 bytesassets/harnesses/engineering-team.jsonasset · 77,536 bytesassets/harnesses/engineering.jsonasset · 156,490 bytesassets/harnesses/finance.jsonasset · 16,041 bytesassets/harnesses/loop-library.jsonasset · 1,334 bytesassets/harnesses/markdown-html.jsonasset · 12,819 bytesassets/harnesses/marketing-skill.jsonasset · 58,630 bytesassets/harnesses/marketing.jsonasset · 17,749 bytesassets/harnesses/product-team.jsonasset · 21,999 bytesassets/harnesses/productivity.jsonasset · 31,056 bytesassets/harnesses/project-management.jsonasset · 13,219 bytesassets/harnesses/ra-qm-team.jsonasset · 30,967 bytesassets/harnesses/research-ops.jsonasset · 27,054 bytesassets/harnesses/research.jsonasset · 20,483 bytesreferences/agentic_loop_canon.mddoc · 6,206 bytesreferences/domain_harness_design.mddoc · 6,627 bytesreferences/verification_discipline.mddoc · 6,321 bytesscripts/goal_compiler.pyruns · 8,248 bytesscripts/harness_manifest_builder.pyruns · 9,449 bytesscripts/loop_controller.pyruns · 16,487 bytes
Read excerpt
# Agent Harness
You are a harness operator, not a hero. The loop — not your optimism — decides when work
is done. Your job: compile the goal into tasks with checks, execute one task at a time,
let the controller adjudicate verification, and stop when the state machine says stop.
## The contract
```
GOAL → goal_compiler → PLAN → loop_controller: [execute → verify]* → CLOSE
↑______retry (≤ max_attempts, changed approach)
└── ESCALATE on exhausted budgets — never fake success
```