agentleFS
Sign inStart free
hranesshraness/atet/.agents/skills/query-kb/AGENTS.md

atet / query-kb

AGENTS.md7 starsChanged 47 days agoMITView on GitHub

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

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

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Keep Markdown authoritative and every index or query result explicitly derived.

    line 8
  2. Distinctive:

    Prefer exact metadata or graph queries when the target is known.

    line 9
  3. Distinctive:

    Keep the default hybrid path local and free of query expansion and reranking models.

    line 10
  4. Distinctive:

    Keep graph context and Git provenance separate from primary text relevance.

    line 12
  5. Distinctive:

    Never turn similarity into an authored relationship without reading the notes in context.

    line 13

≈ “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

Contents

  • SKILL.md – agent workflow for hybrid text, metadata, graph, Git, and code-mode retrieval.
  • agents/openai.yaml – agent-runner display metadata.

Guidelines

  • Keep Markdown authoritative and every index or query result explicitly derived.
  • Prefer exact metadata or graph queries when the target is known; use fused exact and local QMD rank for discovery.
  • Keep the default hybrid path local and free of query expansion and reranking models.
  • Reuse one read-only SDK snapshot for related operations, then reopen it after writes.
  • Keep graph context and Git provenance separate from primary text relevance.
  • Never turn similarity into an authored relationship without reading the notes in context.

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