agentleFS
Sign inStart free
kyto64kyto64/aidd-template-scale/AGENTS.md

aidd-template-scale

AGENTS.md0 starsChanged 2 months agoMITView on GitHub

Please also reference the following rules as needed. The list below is provided in TOON format, and @ stands for the project root directory. rules[6]: - path: @.codex/memories/code-style.md description: Coding conventions applyTo[1]: */ - path: @.codex/memories/docker-compose-local.md description: Docker Compose (local development) applyTo[1]: docker-dev/* - path: @.codex/memories/git-worktree.md description: Git worktree workflow applyTo[1]: */* - path: @.codex/memories/git.md description: Git conventions applyTo[1]: */ - path: @.codex/memories/github-cli-pr.md description: GitHub CLI — PR and Issues applyTo[1]: */ - path: @.codex/memories/ticket-driven-workflow.md description: Ticket-driven workflow applyTo[1]: */

The file

Create a free account to mount
Files
AGENTS.md

Please also reference the following rules as needed. The list below is provided in TOON format, and @ stands for the project root directory.

rules[6]:

  • path: @.codex/memories/code-style.md description: Coding conventions applyTo[1]: */
  • path: @.codex/memories/docker-compose-local.md description: Docker Compose (local development) applyTo[1]: docker-dev/**
  • path: @.codex/memories/git-worktree.md description: Git worktree workflow applyTo[1]: */
  • path: @.codex/memories/git.md description: Git conventions applyTo[1]: */
  • path: @.codex/memories/github-cli-pr.md description: GitHub CLI — PR and Issues applyTo[1]: */
  • path: @.codex/memories/ticket-driven-workflow.md description: Ticket-driven workflow applyTo[1]: */
<!-- SSOT: Edit .rulesync/rules/ and run `rulesync generate`. Generated: CLAUDE.md, AGENTS.md, .claude/, .cursor/rules/, .codex/memories/, .agents/skills/, .mcp.json -->

Project overview

AI-driven development template (lean). Replace placeholders with your project details.

Tech stack (placeholder)

  • Application: (fill in after adopting this template)
  • CI/CD: GitHub Actions
  • Issue tracking: GitHub Issues + gh

Documentation (SSOT)

Markdown under docs/ is the Single Source of Truth for specifications. When docs and code disagree, code wins unless you explicitly update docs in the same PR.

  • docs/_inventory.md — inventory and SSOT boundaries
  • docs/product/index.md — product
  • docs/architecture/index.md — architecture
  • docs/operations/index.md — operations
  • docs/development/index.md — development

See README.md for adoption checklist.

Development workflow

Ticket-driven development using GitHub Issues. Setup: docs/development/ticket-driven-setup.md.

Skills (.claude/skills/):

  • /start-ticket <issue-number> — start issue, plan, implement, open PR
  • /address-pr-feedback <pr-number> — address review feedback
  • /close-ticket <issue-number> — post-merge docs update
  • /spec-lookup — answer from docs/ (code when needed)

Cursor

  • Skills: .claude/skills/ (Cursor reads them as Agent Skills)
  • Project rules: .rulesync/rules/ → rulesync generate → .cursor/rules/

Codex CLI

  • Rules: .codex/memories/ (generated)
  • Skills: .agents/skills/ (generated)

AI settings changes

Edit .rulesync/ only, then rulesync generate and commit generated files. Do not edit generated files directly.

Language

  • User-facing docs and PR descriptions: Japanese (unless your team chooses otherwise)
  • Code comments: English

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