agentleFS
baksohyeonbaksohyeon/mogui-agent-harness/AGENTS.md

mogui-agent-harness

AGENTS.md1 starsChanged 4 months agoMITView on GitHub

This file is a router. It points to where to read, not the content itself. Keep it under 100 lines. Claude Code reads CLAUDE.md, Codex reads AGENTS.md. Cursor uses .cursor/rules/agentic-router.mdc as its project rule adapter. CLAUDE.md, AGENTS.md, .cursorrules, and .windsurfrules share identical content. Automatic memory update: "remember / don't forget / from now on / don't do" triggers an immediate write to Memory.md (protocol = Instructions.md § Memory Update Protocol). If .setup-done is missing, or the project's content files still…

  • 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 33,315 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

7 rules. About 0 are common, 1 is distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If .setup-done is missing, or the project's content files still contain unfilled double-brace template placeholders (for example the Code …

    line 17
  2. Very specific:

    Keep open questions in .planning/threads/ instead of locking them into an ADR.

    line 57
  3. Very specific:

    After writing an important guide/ADR/postmortem, run a Review Gate Quiz of up to 3 questions before commit/push/PR.

    line 58
  4. Very specific:

    After a long workflow, leave a handoff snapshot in docs/wiki/postmortem/temp/.

    line 59
  5. Very specific:

    Do not commit directly to dev (it is the integration branch).

    line 64
  6. Very specific:

    Avoid English-to-Korean calque slang.

    line 71
  7. Distinctive:

    No emojis in committed files (a hook blocks them).

    line 73

≈ “Common” is an estimate: at least 1 in 5 of the 42,283 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

Project Instructions: {{product-name}}

This file is a router. It points to where to read, not the content itself. Keep it under 100 lines. Claude Code reads CLAUDE.md, Codex reads AGENTS.md. Cursor uses .cursor/rules/agentic-router.mdc as its project rule adapter. CLAUDE.md, AGENTS.md, .cursorrules, and .windsurfrules share identical content.

Always read before answering

  • .agent/Instructions.md: Who/What/Rules/Outputs
  • .agent/Context.md: product, team, stack, and decisions SoT
  • .agent/Memory.md: preferences/corrections learning log

Automatic memory update: "remember / don't forget / from now on / don't do" triggers an immediate write to Memory.md (protocol = Instructions.md § Memory Update Protocol).

First-entry autonomous bootstrap

If .setup-done is missing, or the project's content files still contain unfilled double-brace template placeholders (for example the Code safety bullets below), setup has not been completed. Run the appropriate flow yourself instead of telling the human to type commands:

  • Empty/greenfield target: run bash scripts/setup.sh, then fill the remaining placeholders by asking the user (see PROMPTS.md #1). setup.sh writes .setup-done when it completes.
  • Existing project target: from a separate clone of this starter, run bash scripts/ingest.sh <target-repo-path> (non-destructive; it refuses to run when SOURCE and TARGET resolve to the same directory). Then report the gap report and any *.starter conflicts for the human to adjudicate. After merging, run bash scripts/setup.sh to finalize .setup-done — unless ingest warned about an existing husky/lefthook chain, in which case skip setup.sh (it rewires core.hooksPath) and merge .githooks/pre-commit automation into the existing chain by hand (see PROMPTS.md #2).

This contract is host-agnostic: Claude Code and Codex must behave identically here, with no Claude-specific tooling assumed. After either flow, still read .agent/Instructions.md, .agent/Context.md, and .agent/Memory.md before answering.

Required and recommended tools

ToolVerifyInstall
code-review-graphcode-review-graph statusuvx code-review-graph serve or see the MCP config
GSDwhich gsd-toolsnpx @opengsd/gsd-core@latest
gstackcommand -v gstack (or set GSTACK_HOME)git clone --depth 1 https://github.com/garrytan/gstack.git <host-skills-dir>/gstack && (cd <host-skills-dir>/gstack && ./setup)
Superpowerscheck the host plugin managerinstall per host

Workflow definitions live in .agent/workflows/triple-crown.md.

Code safety (load-bearing, fill in per project)

  • {{e.g. run the apply command after adding a migration}}
  • {{e.g. never print or commit secrets/credentials}}
  • {{stack-specific silent failure pattern}}

GSD and the LLM wiki

  • .planning/ = GSD execution state. Use workstreams for large efforts, workspace for isolation, thread for open discussions, quick for small recording tasks, fast for trivial changes, and capture for collecting input.
  • docs/wiki/ = long-term knowledge. Decisions go in decisions/D-*.md, operational guides in guides/, retrospectives in postmortem/.
  • GSD does not supersede the LLM wiki. GSD holds execution state; the wiki holds long-term knowledge.
  • code-review-graph MCP = a map of the code structure. Use it first when exploring code or checking the impact of a change. Do not treat it as a document search engine.

Directory conventions

  • .agent/ (singular) = Layer 2 context (Instructions/Context/Memory/workflows). Change it freely.
  • .agents/ (plural) = external skill library. Do not rename it.
  • docs/wiki/ = Layer 3 wiki (decisions/postmortem/guides).

Documentation operations

  • Decisions are D-YYYYMMDD-<author>-<slug>.md (copy D-template.md). After writing one, run bash scripts/decisions-index.sh to regenerate the index.
  • Keep open questions in .planning/threads/ instead of locking them into an ADR.
  • After writing an important guide/ADR/postmortem, run a Review Gate Quiz of up to 3 questions before commit/push/PR.
  • After a long workflow, leave a handoff snapshot in docs/wiki/postmortem/temp/.

Branch policy

  • Work on a feat|fix|docs|chore/<topic> branch, then open a PR into dev.
  • Do not commit directly to dev (it is the integration branch).
  • Promote dev to main only at release time.

Optional: Korean-language projects

These rules apply only when the project writes in Korean. Skip them for English-only projects.

  • Avoid English-to-Korean calque slang. Use the approved alternatives in .agent/korean-persona.md.
  • Match the Korean voice and tone defined in .agent/korean-persona.md.
  • No emojis in committed files (a hook blocks them).

Keep the router under 100 lines. Move the body to .agent/ if it grows.

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.