Agents Md Generator

Keeps your AGENTS.md files lean and up to date across monorepos and nested modules. It reads your package manifests, Makefiles, and CI configs to infer real commands instead of inventing them, then generates or repairs both root and module-level agent instructions while staying under 60 and 40 lines respectively. The progressive disclosure approach pushes detail into docs and skills rather than bloating the instructions. Handles the annoying bits like detecting module boundaries, preserving security warnings from existing files, and adapting skill references based on whether you have a local skill directory or rely on external ones. Useful when your agent context is missing, contradictory, or sprawling across a growing codebase.

skills.sh installs: 384
GitHub stars: 112
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add madteacher/mad-agents-skills --skill agents-md-generator --agent claude-code

Installs into .claude/skills of the current project.

Files

AGENTS.md Generator (Root + Nested, Portable)

Goal

Maintain small, high-signal AGENTS.md files:

Root AGENTS.md — purpose of repository, navigation, universal toolchain, canonical commands, links to docs and skills.
Nested AGENTS.md — module/package purpose, local commands, module references.

Use progressive disclosure: keep AGENTS.md concise; push details to docs or skills.

Skill location (agent-specific)

Do NOT assume .agents/ or any fixed directory exists.
Skills may live:
- inside the repository (embedded),
- or in an external/global skill library (external).
If referencing local skills, use only an existing skill root already used by the project or an existing project path already mentioned by repo docs.
If no local skill directory exists — reference skills by name only (external).
Never create hidden agent directories just to store skills.