agentleFS
Sign inStart free
youkistudiosyoukistudios/harness-axis/skills/harness-forge/SKILL.md

harness-forge

Skill0 starsChanged 4 months agoApache-2.0View on GitHub

Create a baseline-bound, impact-aware improvement plan from a verified Harness Axis run. Use when asked how to improve, relocate, consolidate, retire, or change a reviewed harness safely.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run harness forge-plan RUN_DIR --target TARGET --change CHANGE.json --output PLAN_DIR.

    line 13
  2. Very specific:

    Read IMPACT.json, PLAN.json, and APPROVALS.json.

    line 14
  3. Very specific:

    Stop at human review. grants_mutation is false and mutation_supported is false.

    line 15

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Harness Forge — plan-only alpha

Forge plans against evidence. It does not mutate in this alpha.

  1. Require a verified Harness Axis run; run harness verify RUN_DIR.
  2. Author a small change JSON with summary and safe target-relative paths. Do not include secrets or absolute private paths.
  3. Run harness forge-plan RUN_DIR --target TARGET --change CHANGE.json --output PLAN_DIR. The target identity must match the frozen run; output must be outside both target and run.
  4. Read IMPACT.json, PLAN.json, and APPROVALS.json. Name direct dependents, unknown external inbound callers, invariants, required tests, rollback requirements, and numbered pending items.
  5. Stop at human review. grants_mutation is false and mutation_supported is false. Never imply that approval applies changes.

A plan is not proof of safety. No apply, cleanup, move, delete, or rewrite path exists in the alpha.

Download now (ZIP)

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