agentleFS
Sign inStart free
vanillagreencomvanillagreencom/kendex/tools/AGENTS.md

kendex / tools

AGENTS.md76 starsChanged 2 months agoMITView on GitHub

This repository's own scripts and the exclusion lists its commit guards read. Nothing here is catalog content: these run in this repository's commit chain and in CI, never on a consumer's machine.

The file

Create a free account to mount
Files
AGENTS.md

tools/

This repository's own scripts and the exclusion lists its commit guards read. Nothing here is catalog content: these run in this repository's commit chain and in CI, never on a consumer's machine.

  • A script's suite belongs at tests/<n>.test.sh, where the guards shard of ../.github/workflows/skill-tests.yml runs it; release-channel-point is the one script with none, exercised from ../crates/cli/tests/release_workflow/ instead.
  • An exclusion list is <n>-excludes, read by the one commit-guards lane named in its own header; the row format and what may be excluded are ../skills/commit-guards/SKILL.md.
  • guard and setup are described in the root ../AGENTS.md § Commands; guard is where a repo-specific rule is added, one lane per rule.
  • bash32-lint and bash32-parse hold this directory and the shell the catalog ships to Bash 3.2; where each runs is ../skills/AGENTS.md.
  • release-digests and release-channel-point belong to the release feed, which ../docs/architecture/updates.md covers.
  • harness-smoke answers which harness CLIs are usable on the machine it runs on; it reads installed CLIs and writes nothing to the repository.

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