agentleFS
Sign inStart free
codeboehmcodeboehm/maxim/skills/index/SKILL.md

index

Skill0 starsChanged 4 months agoMITView on GitHub

Deterministically catalog and search a project's .agents/ artifacts (prompts, specs, plans, verifications) plus project.md's sections into .agents/index.md, so other skills can look up prior work without rereading full files. Provides reindex.sh (regenerate the catalog from the artifacts' own headers) and query.sh (keyword pre-filter over the catalog, falling back to full-text search). Consumed automatically by the other skills' persist and context-loading steps; also directly invocable for an ad hoc "what's already been done here" query or a manual rebuild after hand-editing .agents/.

7 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use release.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    release

    Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    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:

    Never hand-edit .agents/index.md — it is generated.

    line 38
  2. Very specific:

    No new runtime dependency: bash + coreutils only, same as skills/verify/preflight.sh.

    line 42

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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
SKILL.md

This skill has no LLM judgment step of its own — it is a thin wrapper around two deterministic scripts, the same way verify wraps preflight.sh. When invoked directly, run one of the scripts below (next to this skill, wherever your agent loaded it from — ~/.vibe/skills/index/, ~/.claude/skills/index/, or .github/skills/index/) and report the result.

reindex.sh [project-root]

Regenerates .agents/index.md in full on every run — never an incremental append or merge. It rescans .agents/{prompts,specs,plans,verifications}/*.md and .agents/project.md and extracts Type/Slug/Date/Status/Title/Links straight from each artifact's own structured header (the same - **Field:** lines the prompt/specify/implement/verify templates already require), plus a heading→line-number map for project.md's sections. Because nothing is ever appended, there is no "stale row pointing at a deleted file" state to repair — deleting an artifact and rerunning removes its row automatically.

query.sh <keyword> [<keyword> ...]

A deterministic keyword pre-filter, not a relevance oracle. It always runs reindex.sh first, then greps the index for the given keywords (matching against every column, in practice mostly hitting Slug/Title), falling back to a full-text search across the artifact directories if nothing matches the index. This mechanizes matching, not relevance — a keyword hit is a mechanical fact ("this string appears here"); deciding whether the matched artifact is actually relevant to the current task is still the calling skill's judgment call, the same call it would make reading a directory listing. Never read a query.sh result as proof of relatedness.

Rules

  • Never hand-edit .agents/index.md — it is generated; rerun reindex.sh.
  • Other skills call query.sh (never open .agents/index.md directly) so that what they see is always current, regardless of whether an earlier skill's own "refresh the index" step actually ran.
  • No new runtime dependency: bash + coreutils only, same as skills/verify/preflight.sh.

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