agentleFS
Sign inStart free
SupersynergySupersynergy/agent-token-saver/AGENTS.md

agent-token-saver

AGENTS.md8 starsChanged 3 months agoMITView on GitHub

Portable context reduction. Hooks stay fail-open; optional tools stay optional. - Preserve user changes. No destructive Git. - Smallest change. Tests for behavior. ADR for durable design decisions. - Public files: no private paths, credentials, PIDs, transcripts or host-only claims. - Portable core first. Third-party CLIs are detected, never silently installed. - Hook code receives JSON, returns JSON or nothing, and never changes approval, sandbox or stop ownership. - No maintenance scan in a hook. synx doctor is manual-only. -…

  • 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 repository4 other files it gives its agents.

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    No maintenance scan in a hook.

    line 22

≈ “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
<!-- REPO-POLISH-AGENTS:START -->

Agent Token Saver

Portable context reduction. Hooks stay fail-open; optional tools stay optional.

Commands

  • setup: uv sync --extra dev
  • test: uv run pytest -q
  • lint: uv run ruff check scripts integration tests
  • smoke: bash scripts/neutral_install_smoke.sh
  • live install check: agent-token-saver doctor --profile teams --json

Rules

  • Preserve user changes. No destructive Git.
  • Smallest change. Tests for behavior. ADR for durable design decisions.
  • Public files: no private paths, credentials, PIDs, transcripts or host-only claims.
  • Portable core first. Third-party CLIs are detected, never silently installed.
  • Hook code receives JSON, returns JSON or nothing, and never changes approval, sandbox or stop ownership.
  • No maintenance scan in a hook. synx doctor is manual-only.
  • One controller; workers get one capsule, one oracle, zero or one skill and a compact evidence result. Three independent workers maximum by default.

Product boundary

  • minimal: CLI/ledger only.
  • lean: compact host default, prompt gate, session guard and optional routing/projection CLIs.
  • teams: Lean plus Claude's worker-capsule hook; no automatic fan-out.
  • heavy: opt-in graph/large-context tools for one session.

Codex and Claude use merged JSON hooks plus compact global defaults. Hermes uses a managed block in an existing SOUL.md; GG Coder uses the home AGENTS.md; both retain installed skills for explicit full loading. Verify active configuration with the doctor; files on disk are not proof.

References

  • README: install and user-facing contract.
  • playbook: phase-by-phase usage path and version drift.
  • hooks: host matrix.
  • tooling: default versus optional layers.
  • measurement: method and limits.
<!-- REPO-POLISH-AGENTS:END -->

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