200-agents-md — Claude Code skill: what it does, how to install
Builds an AGENTS.md file for Java repositories via an interactive step-by-step interview. It organizes project stack, Git rules, and AI contributor boundaries.
npx skills add jabrena/plinth --skill 200-agents-md -a claude-codeWhat 200-agents-md does
The skill guides an interactive question session to document Java project conventions inside AGENTS.md. The resulting file details the build tool, frameworks, directory layout, and Git branching rules. Contributor rules use explicit markers: "✅ Always do", "⚠ Ask first", and "🚫 Never do".
Execution relies on templates from references/200-agents-md.md after inspecting existing repository files. Running a Maven validation beforehand is not required. When project goals look ambiguous or tools are missing, the assistant stops to ask for clarification.
What it helps with
- create repository guidelines for AI coding assistants in Java projects
- document build, test, and deployment commands in one place
- define contributor boundaries with explicit permission levels
- standardize Git commit formats and branch workflows
Example prompts for the agent
- Create an AGENTS.md file for this Java repository
- Update AGENTS.md to match our current test commands and Git workflow
- Add contributor boundaries and directory permissions to AGENTS.md
How to install 200-agents-md
1Skills CLI (Vercel)
npx skills add jabrena/plinth --skill 200-agents-md -a claude-code2Manually: put the files in place
~/.claude/skills/200-agents-md/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/200-agents-md/
1Skills CLI (Vercel)
npx skills add jabrena/plinth --skill 200-agents-md -a codex2Manually: put the files in place
.agents/skills/200-agents-md/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add jabrena/plinth --skill 200-agents-md -a cursor2Manually: put the files in place
.cursor/skills/200-agents-md/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install jabrena/plinth 200-agents-md2Manually: put the files in place
.github/skills/200-agents-md/SKILL.md1Skills CLI (Vercel)
npx skills add jabrena/plinth --skill 200-agents-md -a gemini-cli2Platform CLI
gemini skills install https://github.com/jabrena/plinth --path skills/200-agents-mdManually: put the files in place
.devin/skills/200-agents-md/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add jabrena/plinth --skill 200-agents-md -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about 200-agents-md
How to install 200-agents-md in Claude Code?
Run npx skills add jabrena/plinth --skill 200-agents-md -a claude-code in your terminal.
What does 200-agents-md do?
It conducts an interactive interview to create a structured AGENTS.md file for a Java project. The document captures tools, workflows, and strict boundaries for AI agents.
Is Maven validation required before running the skill?
No Maven check is needed. The agent only needs access to inspect project files and documentation before starting the interview.
Source text
SKILL.md · Apache-2.0
--- name: 200-agents-md description: Use when you need to generate an AGENTS.md file for a Java repository — covering project conventions, tech stack, file structure, commands, Git workflow, and contributor boundaries — through a modular, step-based interactive process that adapts to your specific project needs. This should trigger for requests such as Create AGENTS.md; Update AGENTS.md file; Add agent instructions; Generate contributor instructions for Java agents; Document repository conventions in AGENTS.md. Part of Plinth Toolkit license: Apache-2.0 metadata: author: Juan Antonio Breña Moral version: 0.19.0 --- # AGENTS.md Generator for Java repositories Generate a comprehensive AGENTS.md file for Java repositories through a modular, step-based interactive process that covers role definition, tech stack, file structure, commands, Git workflow, and contributor boundaries. **This is an interactive SKILL**. **What is covered in this Skill?** - AGENTS.md generation for Java repositories of any complexity - Role and expertise definition for AI agents and contributors - Tech stack documentation: language, build tool, frameworks, pipelines - File structure mapping with read/write boundaries - Command catalogue for build/test/deploy/run workflows - Git workflow conventions: branching strategy, commit message format - Contributor boundaries using ✅ Always do / ⚠ Ask first / 🚫 Never do formatting ## Constraints No Maven validation is required before generating AGENTS.md. Review the project structure and existing documentation before starting to provide accurate answers during Step 1. - **BEFORE STARTING**: Review the project structure and existing documentation to provide accurate answers during Step 1 - **BEFORE APPLYING**: Read the reference for detailed good/bad examples, constraints, and safeguards for each AGENTS.md generation pattern - **EDGE CASE**: If the user goal is ambiguous, stop and ask a clarifying question before editing files or running project-wide commands - **EDGE CASE**: If required context, files, credentials, or tools are missing, report the blocker explicitly and ask whether to proceed with setup or fallback guidance - **EDGE CASE**: If requested changes conflict with project constraints or safety boundaries, explain the conflict and ask for user confirmation on the preferred trade-off ## When to use this skill - Create AGENTS.md - Update AGENTS.md file - Add agent instructions - Generate contributor instructions for Java agents - Document repository conventions in AGENTS.md ## Workflow 1. **Review repository context before drafting** Inspect project structure and existing documentation to prepare accurate responses for the AGENTS.md discovery phase. 2. **Read AGENTS generation reference** Read `references/200-agents-md.md` and follow its generation patterns and safeguards. 3. **Run interactive requirements capture** Gather role, tech stack, commands, workflow, and boundaries in a modular step-based conversation. 4. **Generate AGENTS.md artifact** Create AGENTS.md with ✅ Always do / ⚠ Ask first / 🚫 Never do boundaries and repository-specific conventions. ## Reference For detailed guidance, examples, and constraints, see [references/200-agents-md.md](references/200-agents-md.md).
© Juan Antonio Breña Moral · Apache-2.0 · jabrena/plinth