agentleFS
Sign inStart free
timursafiullintimursafiullin/aod/skills/init/SKILL.md

init

Skill0 starsChanged 29 days agoApache-2.0View on GitHub

Set up Architect-Orchestrated Development in the current git repository - scaffolds .agents/ project memory, AGENTS.md, CLAUDE.md, aod.config.json and the task ledger. Use when the user wants to start using AOD in a project.

142 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • gaebalaiSkill

    codex-system

    PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".

    Also in 3 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 130 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Check the environment first: node "${CLAUDE_PLUGIN_ROOT}/scripts/aod.mjs" doctor Stop and relay the hints if a required check fails.

    line 8
  2. Distinctive:

    Stop and relay the hints if a required check fails.

    line 10
  3. Very specific:

    Add --slots N if the user asked for a different number of parallel implementers (default 2).

    line 13

“Common” is measured: kept by at least 6 in 10 of the 130 edited versions of this file we could read. “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
SKILL.md

Initialise AOD in this repository

  1. Check the environment first: node "${CLAUDE_PLUGIN_ROOT}/scripts/aod.mjs" doctor Stop and relay the hints if a required check fails.
  2. Scaffold (idempotent; existing files are never overwritten): node "${CLAUDE_PLUGIN_ROOT}/scripts/aod.mjs" init Add --slots N if the user asked for a different number of parallel implementers (default 2).
  3. Relay what was created and skipped, and every line of notes.
  4. Offer to fill in .agents/context/vision.md, .agents/context/invariants.md, .agents/plans/roadmap.md (milestones) and the Commands section of AGENTS.md together with the user. Ask for the product description, red lines, milestones and test commands; write them in English, short and checkable.
  5. Show the model routing (aod route show; default preset max). If the user wants to spend less of the Codex quota, aod route preset economy or balanced.
  6. Offer a session baseline: set session.baseline in .agents/aod.config.json to the project's fast checks (for example ["node --test"], the test command from AGENTS.md). /aod:session-start runs it before any new work.
  7. Offer to turn on the "done means green" gate: set stop_gate.enabled: true and stop_gate.commands (for example ["npm test"]) in .agents/aod.config.json. Then a turn cannot end with uncommitted changes while those commands fail.
  8. Suggest committing the scaffold on the base branch (chore: set up AOD). Do not commit without the user's go-ahead.

Notes:

  • Worktree slots are created on the first delegation, next to the repository in ../<repo>-worktrees/codex-N.
  • .agents/tasks/index.json is the source of truth for tasks; never edit index.md by hand.

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