agentleFS
Sign inStart free
100yenadmin100yenadmin/fable-token-saving-skills-orchestrator/AGENTS.md

fable-token-saving-skills-orchestrator

AGENTS.md100 starsChanged 4 months agoMITView on GitHub

This repository packages public Fable orchestration practices. 1. Read README.md for the public promise and proof boundary. 2. Read SECURITY.md before touching hooks, installer behavior, credentials, or private-data handling. 3. Create or reuse a GitHub issue before meaningful implementation work. 4. Keep all examples public-safe. - CLAUDE.md content is additive, not replacement guidance. - Installer behavior defaults to dry-run and requires --apply for mutation. - Hooks must be idempotent and fail-open. - Never add hardcoded API tokens, cookies, raw transcripts,…

  • 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 31,542 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 repository5 other files it gives its agents.

The file

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

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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 README.md for the public promise and proof boundary.

    line 7
  2. Very specific:

    Read SECURITY.md before touching hooks, installer behavior, credentials, or private-data handling.

    line 8
  3. Distinctive:

    Create or reuse a GitHub issue before meaningful implementation work.

    line 10
  4. Distinctive:

    Keep all examples public-safe.

    line 11
  5. Distinctive:

    Never add hardcoded API tokens, cookies, raw transcripts, customer data, or machine-local private paths.

    line 18
  6. Distinctive:

    Keep Fable-first language, but make lane names configurable.

    line 20
  7. Distinctive:

    Do not claim guaranteed savings or official endorsement.

    line 21
  8. Distinctive:

    Run focused checks before PR readiness claims:

    line 25

≈ “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

Agent Instructions

This repository packages public Fable orchestration practices.

Before Editing

  1. Read README.md for the public promise and proof boundary.
  2. Read SECURITY.md before touching hooks, installer behavior, credentials, or private-data handling.
  3. Create or reuse a GitHub issue before meaningful implementation work.
  4. Keep all examples public-safe.

Invariants

  • CLAUDE.md content is additive, not replacement guidance.
  • Installer behavior defaults to dry-run and requires --apply for mutation.
  • Hooks must be idempotent and fail-open.
  • Never add hardcoded API tokens, cookies, raw transcripts, customer data, or machine-local private paths.
  • Keep Fable-first language, but make lane names configurable.
  • Do not claim guaranteed savings or official endorsement.

Validation

Run focused checks before PR readiness claims:

python3 -m unittest discover -s tests
python3 scripts/check_docs.py

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