agentleFS
Sign inStart free
indyforgeindyforge/knowledge-forge/AGENTS.md

knowledge-forge

AGENTS.md0 starsChanged 5 months agoMITView on GitHub

Knowledge Forge is a local-first maintainer workbench for source-backed Markdown archives and auditable agent-assisted workflows. The public v0.2 core captures local HTML fixtures into source-backed Markdown notes and manifests, and turns local issue or pull-request JSON into maintainer briefs with exact source snapshots, SHA-256 provenance, evidence gaps, and explicit local writes.

  • 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 31,700 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 repository4 other files it gives its agents.

The file

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

9 rules. About 1 is common, 4 are distinctive, and 4 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    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:

    Use $capture-fixture-verification when capture behavior, manifests, snapshots, hashes, fixtures, or Markdown output changes.

    line 11
  2. Very specific:

    Use $maintainer-brief when preparing issue, pull request, source, or release context for human review.

    line 12
  3. Very specific:

    Use $release-review before release notes or tag preparation.

    line 13
  4. Very specific:

    Use $pr-draft-summary when preparing a substantial pull request.

    line 14
  5. Distinctive:

    Keep the capture manifest schema backward-compatible within a minor release.

    line 25
  6. Distinctive:

    Add fixture tests for any change to Markdown output.

    line 26
  7. Distinctive:

    Do not introduce hidden network writes, cloud sync, broad indexing, OCR, or embeddings by default.

    line 27
  8. Common:

    Do not commit personal vault paths, cookies, API keys, private notes, local database contents, or raw user-private captures.

    line 32
  9. Distinctive:

    Keep writes explicit and previewable.

    line 35

≈ “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

Knowledge Forge is a local-first maintainer workbench for source-backed Markdown archives and auditable agent-assisted workflows.

The public v0.2 core captures local HTML fixtures into source-backed Markdown notes and manifests, and turns local issue or pull-request JSON into maintainer briefs with exact source snapshots, SHA-256 provenance, evidence gaps, and explicit local writes.

Mandatory Workflow Rules

  • Use $capture-fixture-verification when capture behavior, manifests, snapshots, hashes, fixtures, or Markdown output changes.
  • Use $maintainer-brief when preparing issue, pull request, source, or release context for human review.
  • Use $release-review before release notes or tag preparation.
  • Use $pr-draft-summary when preparing a substantial pull request.

Build And Test

  • Test: npm test
  • Syntax check: npm run check
  • Smoke test: npm run smoke
  • Maintainer brief smoke test: npm run smoke:brief

Compatibility Rules

  • Keep the capture manifest schema backward-compatible within a minor release.
  • Add fixture tests for any change to Markdown output.
  • Do not introduce hidden network writes, cloud sync, broad indexing, OCR, or embeddings by default.
  • Preserve human-readable Markdown as the durable storage layer.

Security And Privacy

  • Do not commit personal vault paths, cookies, API keys, private notes, local database contents, or raw user-private captures.
  • Fixtures must be synthetic or explicitly public.
  • Redact local machine-specific paths from examples.
  • Keep writes explicit and previewable.

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