agentleFS
Sign inStart free
fishukefishuke/harness-engineering-skill/assets/AGENTS.md

harness-engineering-skill / assets

AGENTS.md0 starsChanged 25 days agoMITView on GitHub

This file is a map. Keep it under 60 lines. Details live in the linked docs.

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repositoryOne other file it gives its agents.

The file

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

4 rules. About 0 are common, 1 is distinctive, and 3 are 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.

  • 3

    Very specific

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

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

    Run: make dev (isolated instance.

    line 6
  2. Very specific:

    Test: make test · Lint: make lint · Logs: scripts/logs.sh '<query>'

    line 7
  3. Distinctive:

    Before opening a PR: tests green, lint green, evidence of the change attached (screenshot or log excerpt).

    line 8
  4. Very specific:

    Ask what tool, doc or rule is missing, then add it.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.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
AGENTS.md

AGENTS.md

This file is a map. Keep it under 60 lines. Details live in the linked docs.

Every task

  • Run: make dev (isolated instance; prints URL)
  • Test: make test · Lint: make lint · Logs: scripts/logs.sh '<query>'
  • Before opening a PR: tests green, lint green, evidence of the change attached (screenshot or log excerpt).

Read before you touch

  • ARCHITECTURE.md for layers, dependency direction and where new code goes.
  • docs/PLANS.md before starting multi-step work; create a plan in docs/exec-plans/active/.
  • docs/RELIABILITY.md before changing anything on a critical path.
  • docs/SECURITY.md before touching auth, secrets or user data.
  • docs/FRONTEND.md and docs/DESIGN.md for UI work.
  • docs/PRODUCT_SENSE.md when the request is ambiguous about what the user wants.

When you are stuck

Ask what tool, doc or rule is missing, then add it. Do not retry blindly. Record debt you notice in docs/exec-plans/tech-debt-tracker.md.

Escalate to a human when

  • A change touches data migration, billing, auth or deletes user data.
  • Acceptance criteria are unclear after reading the product spec.
  • A test is flaky and you cannot make it deterministic in one attempt.

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