agentleFS
asta-nguyenasta-nguyen/agent-devkit/AGENTS.md

agent-devkit

AGENTS.md4 starsChanged 2 months agoMITView on GitHub

The sections below apply only when developing the agent-devkit source repository. When this file is loaded as a plugin rule in another project, follow that project's own AGENTS.md and use using-devkit to choose the workflow; this file imposes no repository-specific policies on that project. This repository contains dependency-free Markdown skills for keeping coding-agent context and an LLM-facing codebase wiki in sync. - Read this file. Read docs/llm/INDEX.md only in target projects where the skills have created that wiki. - Inspect…

The file

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

12 rules. About 1 is common, 8 are distinctive, and 3 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    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:

    Read this file. Read docs/llm/INDEX.md only in target projects where the skills have created that wiki.

    line 15
  2. Distinctive:

    Keep changes focused and minimal.

    line 24
  3. Distinctive:

    Follow the team's one-branch/PR-per-task workflow.

    line 26
  4. Very specific:

    When resolving conflicts in docs/agent-devkit/INDEX.md or docs/llm/INDEX.md, preserve links from every task and verify all targets after …

    line 33
  5. Distinctive:

    Treat generated LLM documentation as a product artifact: update it when the documented code or behavior changes.

    line 36
  6. Distinctive:

    Do not add TypeScript or a build system unless the task explicitly asks for it.

    line 38
  7. Distinctive:

    Never hide errors that could leave code or documentation stale.

    line 42
  8. Common:

    Do not commit secrets, generated dependency directories, or temporary files.

    line 43
  9. Very specific:

    Do not create commits during implementation.

    line 44
  10. Distinctive:

    Run the smallest relevant check after every non-trivial change.

    line 50
  11. Distinctive:

    Prefer explicit instructions and the fewest files possible.

    line 57
  12. Distinctive:

    Only then, write the minimum clear new code that works.

    line 67

≈ “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

Coding Agent Contract

Scope

The sections below apply only when developing the agent-devkit source repository. When this file is loaded as a plugin rule in another project, follow that project's own AGENTS.md and use using-devkit to choose the workflow; this file imposes no repository-specific policies on that project.

This repository contains dependency-free Markdown skills for keeping coding-agent context and an LLM-facing codebase wiki in sync.

Before changing files

  • Read this file. Read docs/llm/INDEX.md only in target projects where the skills have created that wiki.
  • Inspect the existing implementation and its callers before editing relevant files.
  • Reuse the current Markdown skill patterns; do not add scripts, dependencies, or abstractions unless prompt-driven instructions are insufficient.

Working rules

  • Keep changes focused and minimal.
  • Preserve user changes and do not rewrite unrelated files.
  • Follow the team's one-branch/PR-per-task workflow; worktrees are optional. This does not override existing commit or push approval rules.
  • For new change folders and for new spec, plan, decision, estimate, or handoff files, use YYYY-MM-DD-<issue-id>-<slug> before any existing type suffix when an issue ID appears in the task or a related artifact, including its filename. Without one, keep the existing format; never infer an ID or rename an existing artifact.
  • When resolving conflicts in docs/agent-devkit/INDEX.md or docs/llm/INDEX.md, preserve links from every task and verify all targets after the merge.
  • Treat generated LLM documentation as a product artifact: update it when the documented code or behavior changes.
  • Do not add TypeScript or a build system unless the task explicitly asks for it.
  • read-codebase-context and review-and-verify use no-edit subagent briefs. These prompts do not restrict host permissions; parallel execution or subagents assigned file edits need an explicit task.
  • Never hide errors that could leave code or documentation stale.
  • Do not commit secrets, generated dependency directories, or temporary files.
  • Do not create commits during implementation. Leave the working tree for the user to review; commit only after final review-and-verify passes and the user explicitly requests it.

Verification

  • Run the smallest relevant check after every non-trivial change.
  • For workflow changes, exercise the affected skill on a temporary sample repository when its behavior cannot be verified by inspection alone.
  • A change is complete only when its behavior and documentation agree.

Change shape

Prefer explicit instructions and the fewest files possible. If deterministic behavior eventually requires automation, prefer one simple script over a framework. After understanding the affected flow, use this ladder and stop at the first option that satisfies the required behavior:

  1. Does this need to exist at all? Skip speculative work (YAGNI).
  2. Does it already exist in this codebase? Reuse it.
  3. Does the standard library do it? Use it.
  4. Does a native platform feature cover it? Use it.
  5. Does an already-installed dependency solve it? Use it.
  6. Only then, write the minimum clear new code that works.

The ladder never removes explicit requirements, validation at trust boundaries, security, accessibility, or error handling that prevents data loss. For bug fixes, the minimum change is the smallest root-cause fix, not a symptom patch.

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.

Reviews can't be read right now.

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.