agents-md-manager

# AGENTS.md Manager Create and maintain AGENTS.md files and Codex CLI configuration for any project. ## Core Workflow Determine the mode: | Mode | When | Script | |------|------|--------| | **Create** | New project needs AGENTS.md | `scripts/analyze_project.py` then write | | **Refresh** | Existing AGENTS.md needs audit | `scripts/validate_agents_md.py` | | **Convert** | Migrate from CLAUDE.md | `scripts/convert_claude_to_agents.py` | | **Config** | Generate config.toml | `scripts/generate_config_toml.py` | | **Rules** | Create .rules files | See `references/starlark-rules-spec.md` | | **Skills** | Scaffold .agents/skills/ | `scripts/scaffold_codex_skill.py` | ## 1. Project Analysis Run analysis to detect stack, existing config, and gaps: ```bash python3 ~/.claude/skills/agents-md-manager/scripts/analyze_project.py [project_path] ``` Output: JSON report with tech stack, commands, directory structure, and Codex artifact inventory (AGENTS.md, config.toml, .rules, .agents/skills/, CLAUDE.md conversion candidates). ## 2. AGENTS.md Generation Apply the WHAT/WHY/HOW framework in **plain markdown only**—no `@import` syntax, no YAML frontmatter. ### Recommended Sections ```markdown # Project Name Brief description. ## Commands - Dev: `pnpm dev` - Test: `pnpm test` - Build: `pnpm build` - Lint: `pnpm lint` ## Structure - `/src` — Application source - `/tests` — Test suites ## Conventions - [Critical convention 1] - [Critical convention 2] ## Boundaries - Always: Run t...