agentleFS
suiuiui6suiuiui6/harness-engineering-skill/CLAUDE.md

harness-engineering-skill

CLAUDE.md1 starsChanged 2 months agoMITView on GitHub

This repository follows the harness-engineering workflow. Before implementation work: Read these as needed for the selected scope: When the user explicitly wants the structured workflow, invoke /harness-engineering. Ask before irreversible actions or changes that affect shared state outside the local workspace.

The file

We split this CLAUDE.md into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the canonical core files needed for that scope.

    line 11
  2. Distinctive:

    Do not cross a layer gate without evidence.

    line 12
  3. Distinctive:

    If a downstream failure breaks an upstream assumption, roll back minimally.

    line 13
  4. Distinctive:

    Read these as needed for the selected scope:

    line 17
  5. Very specific:

    When the user explicitly wants the structured workflow, invoke /harness-engineering.

    line 28
  6. Distinctive:

    Ask before irreversible actions or changes that affect shared state outside the local workspace.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md 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
CLAUDE.md

Repository Instructions

This repository follows the harness-engineering workflow.

Default Execution Rules

Before implementation work:

  1. Classify the request as bootstrap or maintenance.
  2. Choose the smallest valid start layer.
  3. Read the canonical core files needed for that scope.
  4. Do not cross a layer gate without evidence.
  5. If a downstream failure breaks an upstream assumption, roll back minimally.

Canonical Sources

Read these as needed for the selected scope:

  • SKILL.md
  • core/layer-details.md
  • core/flow.md
  • core/checklists.md
  • core/exit-and-reentry.md
  • adapters/claude-code/host-map.md

Invocation Rule

When the user explicitly wants the structured workflow, invoke /harness-engineering.

Safety Rule

Ask before irreversible actions or changes that affect shared state outside the local workspace.

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.