This skill should be used when creating, auditing, or maintaining AGENTS.md files and Codex CLI configuration for any project—including initializing AGENTS.md for cross-agent compatibility (Codex, Cursor, Copilot, Devin, Jules, Amp, Gemini CLI), generating config.toml or .rules files, scaffolding .agents/skills/, converting CLAUDE.md to AGENTS.md, or auditing existing agent configs for bloat and staleness. Complementary to codex-orchestrator (which executes subagents; this skill creates the config files they consume).
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Create and maintain AGENTS.md files and Codex CLI configuration for any project.
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 |
Run analysis to detect stack, existing config, and gaps:
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).
Apply the WHAT/WHY/HOW framework in plain markdown only—no @import syntax, no YAML frontmatter.
# 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 tests before committing
- Ask: Before adding production dependencies
- Never: Modify migration files directly
## Troubleshooting
- [Common issue and fix]
project_doc_max_bytes)@import, no YAML frontmatterreferences/templates.md for project-type-specific templatesreferences/agents-md-spec.md for discovery and concatenation rulesConvert existing CLAUDE.md to AGENTS.md format:
python3 ~/.claude/skills/agents-md-manager/scripts/convert_claude_to_agents.py <claude_md_path> [output_path]
Outputs AGENTS.md plus conversion_report.json listing transformations and manual review items.
Key transformations: @import inlined or nested; hooks become .rules suggestions; skill invocations become prose; Claude-specific commands stripped.
See references/conversion-mapping.md for the complete field-by-field mapping.
Generate ~/.codex/config.toml (global) or .codex/config.toml (project-scoped):
python3 ~/.claude/skills/agents-md-manager/scripts/generate_config_toml.py [--global | --project <path>] [--model MODEL] [--sandbox MODE]
Covers: model, reasoning effort, personality, sandbox mode, MCP servers, profiles, trusted projects, writable roots.
See references/config-toml-reference.md for the complete field reference.
Create .rules files in Starlark for command approval. Location: ~/.codex/rules/ (global) or .codex/rules/ (project). Rules files are authored manually—no generation script exists for this format. All .rules files in the directory are loaded and merged.
Common patterns:
npm, pip, cargo)rm -rf, git push --force)git commit, gh pr create)See references/starlark-rules-spec.md for syntax and examples.
Scaffold .agents/skills/<name>/ in Codex format (different from Claude .claude/skills/):
python3 ~/.claude/skills/agents-md-manager/scripts/scaffold_codex_skill.py <name> [--path <dir>]
Creates SKILL.md with name + description frontmatter (both required for Codex), plus agents/openai.yaml for UI metadata.
See references/codex-skills-format.md for format differences from Claude skills.
When refreshing existing AGENTS.md, validate:
project_doc_max_bytes limit)@import syntax? (not supported in AGENTS.md)Run automated audit:
python3 ~/.claude/skills/agents-md-manager/scripts/validate_agents_md.py [project_path]
For monorepos, place AGENTS.md at multiple levels:
/AGENTS.md # Repo-wide conventions
/services/
payments/
AGENTS.override.md # Payments-specific overrides
search/
AGENTS.md # Search service conventions
AGENTS.override.md takes precedence over AGENTS.md in the same directorycodex-orchestrator| File | Contents |
|---|---|
references/agents-md-spec.md | AGENTS.md discovery, concatenation, override, size limits, cross-agent compatibility |
references/config-toml-reference.md | Complete config.toml field reference |
references/starlark-rules-spec.md | .rules file syntax, prefix_rule(), decision types |
references/codex-skills-format.md | .agents/skills/ format, openai.yaml, Claude skill differences |
references/conversion-mapping.md | CLAUDE.md to AGENTS.md field-by-field mapping |
references/templates.md | AGENTS.md templates by project type |
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Search academic papers, build literature reviews, and synthesize research findings — combines Exa search (publication category, domain and date filters) with arxiv-mcp-server for paper discovery, download, and deep analysis. Triggers on academic paper, literature review, research synthesis, arxiv, find papers, scholarly search.
The English summary is being prepared. Showing the original description.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
The English summary is being prepared. Showing the original description.
Academic research skill for Biblical Hebrew, Semitic linguistics, cuneiform studies, and comparative Ancient Near Eastern research. Provides Sefaria API for Hebrew Bible, CDLI/ORACC for cuneiform databases, and web discovery via Omnisearch, Exa, Firecrawl, and Obscura for finding scholarly sources across JSTOR, Perseus, Persée, Google Scholar, and academia.edu. Triggers on Hebrew quotes, cuneiform, Sefaria, ANE research, Minoan, search for scholarship, find papers, literature review, scholarly search, academic search, Genesis/Tehom, Ugaritic, Talmudic sources, extract from PDF, OCR academic.
The English summary is being prepared. Showing the original description.
Build comprehensive ARCHITECTURE.md files following matklad's canonical guidelines — bird's-eye views, ASCII/Mermaid diagrams, codemaps, invariants, and layer boundaries. Triggers on document the architecture, create ARCHITECTURE.md, map this codebase, architectural overview.
The English summary is being prepared. Showing the original description.
Generate physically-based atmospheric scattering shaders — sky domes, planetary atmospheres, LUT-optimized pipelines, depth-aware post-processing. Four modes — sky-dome, atmosphere-post, planet, lut. Triggers on atmospheric scattering, sky shader, sunset rendering, planet atmosphere, Rayleigh scattering, Mie scattering, volumetric sky, sky dome, atmosphere post-processing, aerial perspective, transmittance LUT, sky rendering, realistic sky, planetary rendering.
The English summary is being prepared. Showing the original description.
Scaffold and run Karpathy-style autoresearch loops in any git repo. This skill should be used when setting up autonomous code improvement, generating adversarial eval harnesses, running hypothesis-implement-eval-keep/discard loops, or checking autoresearch progress. Triggers on "autoresearch", "autonomous improvement", "eval loop", "hypothesis loop", "self-improvement loop".
The English summary is being prepared. Showing the original description.