agentleFS
zanglgzanglg/dotagents/AGENTS.md

dotagents

AGENTS.md0 starsChanged 17 days agoMITView on GitHub

These instructions apply to the entire repository. This repository stores portable content for a personal .agents workspace: skills, agent-facing instructions, workflow scaffolding, templates, and related development assets. The repository may be edited by agents, so changes should be clear, conservative, and easy to audit. - Preserve existing user work. Do not delete, rewrite, or normalize unrelated local files unless the user explicitly asks. - Keep commits focused on the requested change. Start short-lived feature branches from current main; do not…

The file

Show its rules and text

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

13 rules. About 0 are common, 4 are distinctive, and 9 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 9

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Keep commits focused on the requested change.

    line 18
  2. Distinctive:

    After user approval and validation, integrate each feature through a PR to main using Squash and merge, producing one Conventional Commit.

    line 20
  3. Very specific:

    Use skills/semver-bump/SKILL.md to recommend and update SemVer versions.

    line 29
  4. Very specific:

    Follow CONTRIBUTING.md for this repository's release workflow.

    line 31
  5. Very specific:

    Before preparing commits, read and follow the commit message and commit boundary rules in CONTRIBUTING.md.

    line 34
  6. Very specific:

    Do not commit secrets, tokens, credentials, private machine state, caches, generated scratch output, or .DS_Store.

    line 36
  7. Distinctive:

    Prefer plain text and Markdown for durable documentation.

    line 38
  8. Distinctive:

    Use ASCII unless an existing file or user-facing content clearly calls for another character set.

    line 39
  9. Very specific:

    When adding a reusable skill, put it under skills/<skill-name>/ with a SKILL.md entrypoint.

    line 41
  10. Very specific:

    Keep supporting files near the skill that owns them, such as scripts/, references/, assets/, or templates.

    line 43
  11. Very specific:

    Update VERSION only when preparing an authorized release, together with dated release notes.

    line 46
  12. Very specific:

    Keep repository-wide documentation open to additional skills.

    line 48
  13. Distinctive:

    Document non-obvious behavior in the skill or README instead of relying on tribal knowledge in commit messages.

    line 51

≈ “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

These instructions apply to the entire repository.

Repository Purpose

This repository stores portable content for a personal .agents workspace: skills, agent-facing instructions, workflow scaffolding, templates, and related development assets.

The repository may be edited by agents, so changes should be clear, conservative, and easy to audit.

Working Rules

  • Preserve existing user work. Do not delete, rewrite, or normalize unrelated local files unless the user explicitly asks.
  • Keep commits focused on the requested change. Start short-lived feature branches from current main; do not maintain a long-lived dev branch.
  • After user approval and validation, integrate each feature through a PR to main using Squash and merge, producing one Conventional Commit. Never push directly to main, force-push it, or use merge/rebase merging. Verify the result before deleting the completed feature branch. See CONTRIBUTING.md for the complete workflow and preservation of existing branches.
  • main contains reviewed, usable skills, including changes not yet assigned a version. Keep these under [Unreleased]; prepare version metadata in a separate release PR when requested. Tags, GitHub Releases, and downloadable bundles are optional; create them only when requested.
  • Use skills/semver-bump/SKILL.md to recommend and update SemVer versions. Its scope is version metadata, not branch integration or publication. Follow CONTRIBUTING.md for this repository's release workflow; feature integration, release commits, PR merges, tags, and remote writes require explicit authorization for the relevant action.
  • Before preparing commits, read and follow the commit message and commit boundary rules in CONTRIBUTING.md.
  • Do not commit secrets, tokens, credentials, private machine state, caches, generated scratch output, or .DS_Store.
  • Prefer plain text and Markdown for durable documentation.
  • Use ASCII unless an existing file or user-facing content clearly calls for another character set.
  • When adding a reusable skill, put it under skills/<skill-name>/ with a SKILL.md entrypoint.
  • Keep supporting files near the skill that owns them, such as scripts/, references/, assets/, or templates.
  • Record pending notable changes under [Unreleased] in CHANGELOG.md. Update VERSION only when preparing an authorized release, together with dated release notes. Never bump versions on unfinished feature branches.
  • Keep repository-wide documentation open to additional skills. Group-specific guides belong under docs/<group>/; supporting instructions stay beside the skill that owns them.
  • Document non-obvious behavior in the skill or README instead of relying on tribal knowledge in commit messages.

Validation

Before committing, run:

git status --short

For documentation-only changes, manually review Markdown for clarity and broken relative links. For scripts or generated assets, run the smallest relevant local check and record it in the final response.

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.