agentleFS
Sign inStart free
fhgomesfhgomes/my-awesome-agents-skills/skills/harness-engineer/SKILL.md

harness-engineer

Skill5 starsChanged 40 days agoGPL-3.0View on GitHub

Deeply identify a repository (tech stack, architecture, purpose, patterns, companion projects) and harvest what the team already knows — code patterns, conventions, business rules, war stories — into an AI harness sized to the project. router AGENTS.md, vendor entry files (CLAUDE.md, copilot-instructions, .cursorrules; Codex reads AGENTS.md natively), a docs/ or .ai/ reference folder (tech-info.md, architecture.md, business-context.md, conventions.md, guidelines.md, testing.md, extra-context.md), a versioned constitution.md with Do-Not-Break rules, workflow docs (repository-map, change-workflow, review-checklist...) and focused tech guides (junit-testing-guide.md, spring-backend-guide.md...) with verified commands and golden examples. Identifies the FULL catalog of candidate files, creates only what the repo's size justifies now, records the rest. Use whenever the user asks to create/update AGENTS.md, CLAUDE.md, .cursorrules, or copilot-instructions; to "make this repo AI-ready", "map/identify this project", "create the project constitution"; mentions "harness", "context engineering", or "repository context"; or complains AI keeps breaking things or hallucinating commands in their project. Also triggers on the equivalent phrases in other languages. Any repo-level context/instructions for AI coding tools in ANY form means use this skill.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free