agentleFS
Sign inStart free
LandonTomaineLandonTomaine/LT-Agents/AGENTS.md

LT-Agents

AGENTS.md0 starsChanged 4 months agoMITView on GitHub

This repository stores reusable Codex skills and agent knowledge.

  • 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 repository5 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. Distinctive:

    Do not mix generated collection docs into a skill package unless the skill needs them at runtime.

    line 8
  2. Very specific:

    Keep SKILL.md focused on trigger, purpose, constraints, and workflow.

    line 9
  3. Very specific:

    Put longer task-specific guidance in references/ and load it only when needed.

    line 10
  4. Very specific:

    Put deterministic helpers in scripts/.

    line 11
  5. Distinctive:

    Keep examples concise and portable across repositories.

    line 12
  6. Very specific:

    When running PowerShell commands on Windows, do not use && as a command separator.

    line 13
  7. Distinctive:

    Avoid unrelated formatting churn in skill files.

    line 18
  8. Distinctive:

    Keep repository-level docs short and useful for curation.

    line 19
  9. Common:

    Do not commit local secrets, credentials, generated caches, or temporary Codex state.

    line 20

≈ “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

Repository Agent Instructions

This repository stores reusable Codex skills and agent knowledge.

Rules

  • Preserve skill package boundaries. Keep each skill under skills/<skill-name>/.
  • Do not mix generated collection docs into a skill package unless the skill needs them at runtime.
  • Keep SKILL.md focused on trigger, purpose, constraints, and workflow.
  • Put longer task-specific guidance in references/ and load it only when needed.
  • Put deterministic helpers in scripts/; prefer scripts for repeatable scaffolding and checks.
  • Keep examples concise and portable across repositories.
  • When running PowerShell commands on Windows, do not use && as a command separator. Run sequential commands as separate tool calls, or use clear native PowerShell control flow when one command truly depends on another.

Change Hygiene

  • Review copied skill changes before committing.
  • Avoid unrelated formatting churn in skill files.
  • Keep repository-level docs short and useful for curation.
  • Do not commit local secrets, credentials, generated caches, or temporary Codex state.

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