agentleFS
xixu-mexixu-me/skvlt/AGENTS.md

skvlt

AGENTS.md7 starsChanged 35 days agoMITView on GitHub

This repository is a lightweight Agent Skills manifest repo. The primary artifact is skvlt.yaml, which tracks approved skill sources, installed skill names, and manifest counts. The main companion document is MANIFEST_POLICY.md, which defines how agents should decide whether to add, replace, reject, or escalate manifest changes. There is currently no application code or automated test suite checked into this repository, but there is now a lightweight bun-based formatting toolchain and GitHub Actions formatting workflows. When editing skvlt.yaml: Follow MANIFEST_POLICY.md before…

  • 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 repository2 other files it gives its agents.

The file

Show its rules and text

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

22 rules. About 0 are common, 14 are distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈14

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

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

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

    Treat skvlt.yaml as the primary file.

    line 25
  2. Very specific:

    Keep MANIFEST_POLICY.md aligned with actual maintenance behavior.

    line 26
  3. Distinctive:

    Prefer small, auditable edits over broad manifest churn.

    line 27
  4. Distinctive:

    Do not invent missing metadata about skills.

    line 28
  5. Distinctive:

    Do not add agent-specific, repo-specific, or runtime-bound skills unless the policy explicitly allows them.

    line 29
  6. Very specific:

    Keep total_sources equal to the number of source blocks.

    line 36
  7. Very specific:

    Keep total_skills equal to the sum of all per-source counts.

    line 37
  8. Very specific:

    Keep each source count equal to the number of listed skills in that block.

    line 38
  9. Distinctive:

    Remove a source block entirely if its last skill is removed.

    line 39
  10. Distinctive:

    Avoid duplicate skill names across the manifest.

    line 40
  11. Distinctive:

    Prefer updating an existing trusted source block over adding a new source block.

    line 41
  12. Distinctive:

    Treat source-level additions or removals as higher risk than skill-level additions or removals.

    line 42
  13. Very specific:

    Follow MANIFEST_POLICY.md before making substantive manifest changes.

    line 46
  14. Distinctive:

    Add specialized or dependency-closing skills only when they fit an already trusted source.

    line 50
  15. Distinctive:

    When two general skills substantially overlap, prefer the one that is more complete, more practical, and more worth retaining.

    line 51
  16. Distinctive:

    Before claiming a manifest edit is complete, verify:

    line 57
  17. Distinctive:

    If you need upstream skill discovery, prefer checking the local installed skill files first, then use the relevant skills tooling or …

    line 75
  18. Very specific:

    Update MANIFEST_POLICY.md when maintenance behavior changes.

    line 79
  19. Distinctive:

    Update AGENTS.md when repository layout, validation steps, or working rules change.

    line 80
  20. Distinctive:

    Keep docs concise and operational.

    line 81
  21. Distinctive:

    Keep commits focused on one manifest or documentation change at a time.

    line 85
  22. Very specific:

    Call out count updates explicitly if total_sources, total_skills, or source count fields changed.

    line 88

≈ “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

Project Overview

This repository is a lightweight Agent Skills manifest repo.

The primary artifact is skvlt.yaml, which tracks approved skill sources, installed skill names, and manifest counts.

The main companion document is MANIFEST_POLICY.md, which defines how agents should decide whether to add, replace, reject, or escalate manifest changes.

There is currently no application code or automated test suite checked into this repository, but there is now a lightweight bun-based formatting toolchain and GitHub Actions formatting workflows.

Repository Layout

  • skvlt.yaml - source-of-truth manifest for installed skills
  • MANIFEST_POLICY.md - maintenance policy for agent-driven manifest changes
  • package.json - local formatter entrypoint and scripts
  • .prettierrc.json - repository formatting rules
  • .github/workflows/format-check.yml - formatting validation workflow
  • .github/workflows/format-fix.yml - manual formatting remediation workflow
  • LICENSE - repository license

Working Rules

  • Treat skvlt.yaml as the primary file.
  • Keep MANIFEST_POLICY.md aligned with actual maintenance behavior.
  • Prefer small, auditable edits over broad manifest churn.
  • Do not invent missing metadata about skills; inspect local skill files or trusted upstream sources first.
  • Do not add agent-specific, repo-specific, or runtime-bound skills unless the policy explicitly allows them.

Manifest Editing Instructions

When editing skvlt.yaml:

  1. Preserve the generated header comment if present.
  2. Keep total_sources equal to the number of source blocks.
  3. Keep total_skills equal to the sum of all per-source counts.
  4. Keep each source count equal to the number of listed skills in that block.
  5. Remove a source block entirely if its last skill is removed.
  6. Avoid duplicate skill names across the manifest.
  7. Prefer updating an existing trusted source block over adding a new source block.
  8. Treat source-level additions or removals as higher risk than skill-level additions or removals.

Change Decision Rules

Follow MANIFEST_POLICY.md before making substantive manifest changes.

High-level defaults:

  • Add specialized or dependency-closing skills only when they fit an already trusted source.
  • When two general skills substantially overlap, prefer the one that is more complete, more practical, and more worth retaining; use maintenance and authority as tie-breakers rather than the primary decision rule.
  • Reject skills that are tightly bound to a specific agent, repository, or runtime unless explicitly approved.
  • Escalate ambiguous overlap, close calls between broad general skills, process-shaping changes, or source-level churn to a human.

Validation

Before claiming a manifest edit is complete, verify:

  • repository formatting still passes
  • the YAML remains readable
  • the manifest counts are internally consistent
  • the edited source block count matches the listed skills
  • any dependency-based addition is actually justified by installed skills or policy

Useful local checks:

bun install
bun run format:check

If you need upstream skill discovery, prefer checking the local installed skill files first, then use the relevant skills tooling or trusted upstream listing.

Documentation Updates

  • Update MANIFEST_POLICY.md when maintenance behavior changes.
  • Update AGENTS.md when repository layout, validation steps, or working rules change.
  • Keep docs concise and operational; this repo does not need broad product documentation.

Commit and Review Guidance

  • Keep commits focused on one manifest or documentation change at a time.
  • Mention the affected source or skill family in the commit message when possible.
  • Summarize why a skill was added, replaced, rejected, or escalated.
  • Call out count updates explicitly if total_sources, total_skills, or source count fields changed.

Common Gotchas

  • Forgetting to update manifest counts after editing a source block
  • Leaving an empty source block behind after removing its last skill
  • Adding a skill dependency without adding the dependency itself
  • Treating a specialized skill as a duplicate of a general skill
  • Keeping a skill only because it exists locally, without checking whether it belongs in the manifest

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.