agentleFS
jscraikjscraik/Agent-Skills/skills-system/AGENTS.md

Agent-Skills / skills-system

AGENTS.md9 starsChanged 46 days agoApache-2.0View on GitHub

- Treat this subtree as governed system-skill bridge content, not ordinary first-party skill source. - Preserve upstream lock and bridge contracts. Refresh system skills only through the lock/projection workflow or an explicitly documented migration. - Do not silently fork bundled or system skills. If a local patch is necessary, record the reason, upstream source, expected refresh path, and validation. - Keep creator and installer flow references under the system-skill bridge instead of duplicating long procedures into this AGENTS file. -…

The file

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

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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:

    Treat this subtree as governed system-skill bridge content, not ordinary first-party skill source.

    line 14
  2. Distinctive:

    Do not silently fork bundled or system skills.

    line 18
  3. Distinctive:

    Keep creator and installer flow references under the system-skill bridge instead of duplicating long procedures into this AGENTS file.

    line 20

≈ “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

skills-system Agent Guide

Scope

  • Applies to skills-system/**.
  • Inherits the repository root AGENTS.md.

Edit Policy

  • Treat this subtree as governed system-skill bridge content, not ordinary first-party skill source.
  • Preserve upstream lock and bridge contracts. Refresh system skills only through the lock/projection workflow or an explicitly documented migration.
  • Do not silently fork bundled or system skills. If a local patch is necessary, record the reason, upstream source, expected refresh path, and validation.
  • Keep creator and installer flow references under the system-skill bridge instead of duplicating long procedures into this AGENTS file.

Context Pointers

  • System lock: Infrastructure/GOVERNANCE/skills-system-upstream.lock.json.
  • Repo surface ownership: ../Docs/agents/15-repo-surface-ownership.md.
  • Path ownership: ../Docs/agents/14-path-ownership-boundaries.md.

Validation

  • For system-skill refreshes, run the projection-integrity or upstream-lock validator that owns the changed files.
  • For manual edits, report why the normal refresh path was not used and what downstream runtime surface was or was not proven.

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.

Reviews can't be read right now.

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.