agentleFS
chocomyongchocomyong/harness-kit/skills/harness-setup/SKILL.md

harness-setup

Skill2 starsChanged 28 days agoMITView on GitHub

Set up or absorb the harness-kit operating rules in this repo. Use when the user asks to install harness-kit, set up agent rules, fill AGENTS.md placeholders, or fold harness-kit ideas into existing rules docs.

  • Pipes a download into a shell

7 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

7 rules. 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    If the kit files are not present yet, run the installer from the repo root: curl -fsSL …

    line 19
  2. Very specific:

    Read AGENTS.md and WORK_PROTOCOL.md.

    line 22
  3. Very specific:

    Keep AGENTS.md to rules only and under ~150 lines.

    line 29
  4. Very specific:

    Read harness-kit's MINIMAL.md and principles/absence-judgment.md.

    line 35
  5. Distinctive:

    Read the repo's existing rules docs end to end.

    line 36
  6. Distinctive:

    Create no new rule files unless the user agrees.

    line 44
  7. Distinctive:

    Ask a fresh session: "Summarize the rules file in five bullets and quote the top invariant." An answer that is not from the file means the …

    line 48

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

Set up harness-kit in this repo

Decide which path applies, then follow only that path.

Which path

  • The repo has no rules docs (no AGENTS.md, CLAUDE.md, or house dev guide), or AGENTS.md still contains <PLACEHOLDER> marks -> Fill.
  • The repo already runs its own rules docs -> Absorb. Never install a second rules system beside an existing one: the same rule stated in two places drifts.

Fill

  1. If the kit files are not present yet, run the installer from the repo root: curl -fsSL https://raw.githubusercontent.com/chocomyong/harness-kit/main/install.sh | sh It only adds files and never overwrites.
  2. Read AGENTS.md and WORK_PROTOCOL.md.
  3. Survey the repo: file tree, git log, README and other docs, build and deploy scripts.
  4. Fill every <PLACEHOLDER> in AGENTS.md and docs/REPO_MAP.md with measured facts about this repo. Each value comes from something you read here, not from what similar repos look like.
  5. Section 0 (the top invariant) is confirmed by the human. Propose candidates you found - a production datastore, a one-way sync, a paid API - with the file and line that suggested each. Never invent one.
  6. Keep AGENTS.md to rules only and under ~150 lines. Layout and names go to docs/REPO_MAP.md.
  7. Show the full diff and wait for confirmation before saving. Then delete the HTML guidance comments from the filled files.

Absorb

  1. Read harness-kit's MINIMAL.md and principles/absence-judgment.md.
  2. Read the repo's existing rules docs end to end.
  3. Propose the smallest set of edits that folds into the existing docs, in their language and format:
    • the top invariant stated at the top of the highest-authority doc,
    • absence-judgment as a named rule,
    • an index-first incident registry, seeded with lessons the team keeps re-explaining,
    • the three-question done check (ran / fails when wrong / measured in the right place).
  4. Where a kit idea duplicates one the repo already has, keep theirs and skip the kit's.
  5. Create no new rule files unless the user agrees. Show the diff before saving.

Confirm it loaded

Ask a fresh session: "Summarize the rules file in five bullets and quote the top invariant." An answer that is not from the file means the wiring is broken; fix that before other work.

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.