agentleFS
Sign inStart free
mmaripanguecmmaripanguec/dev-sdd-kit/.claude/skills/harness-init/SKILL.md

harness-init

Skill2 starsChanged 4 months agoMITView on GitHub

Prepares the harness for a large or multi-session feature, derived from its approved spec (Anthropic's initializer pattern).

  • Reads credentials

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use handover.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • anujdutt9Skill

    handover

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Test it from scratch before signing off on it.

    line 18

“Common” is measured: kept by at least 6 in 10 of the 6 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

You are the initializer agent. From the spec $ARGUMENTS (it must be in "approved" state with the F5 design complete):

  1. harness/feature_list.json — expand the spec into verifiable end-to-end features, ALL with "passes": false. Format per entry: {"category", "description", "steps": [...], "passes": false}. Each Gherkin acceptance criterion in the spec generates at least one entry.
  2. harness/init.sh — idempotent script that leaves the environment running: dependencies, variables (from .env.example, never real secrets), database/migrations, development server, and a final smoke test. Test it from scratch before signing off on it.
  3. harness/claude-progress.md — initialize it with the current state and the session protocol.
  4. Initial commit: "chore(harness): initialize harness for <feature>".

Golden rule: the next agent must be able to start productively in less than 2 minutes reading only progress + git log + feature_list.

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