agentleFS
anthrilanthril/vibe-guard/.claude/skills/new-adapter/SKILL.md

new-adapter

Skill2 starsChanged 8 months agoApache-2.0View on GitHub

Scaffold a new VGuard adapter for an AI coding agent. Use when the user says "add adapter", "support a new agent", or wants to integrate VGuard with a new AI tool.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. lbb00/ai-rules-sync★ 37same name
    2. ingsergiovt/claude-code-hexagonal-kit★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the user for these if not provided:

    line 18
  2. Very specific:

    Use the template at .claude/skills/new-adapter/templates/adapter.ts.

    line 29
  3. Very specific:

    Create tests/adapters/<agent-id>.test.ts with tests for:

    line 54
  4. Distinctive:

    All active rules included in output

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Create New VGuard Adapter: $ARGUMENTS

Generate a VGuard adapter that produces agent-specific configuration files.

What This Skill Creates

  1. Adapter file at src/adapters/<agent-id>/adapter.ts
  2. Registration in the CLI commands and type definitions

Required Information

Ask the user for these if not provided:

  • Agent ID: kebab-case identifier (e.g., windsurf, aider)
  • Agent Name: Human-readable (e.g., Windsurf, Aider)
  • Enforcement level: runtime (can block operations) or advisory (guidance only)
  • Output files: What files the adapter generates and where
  • Config format: How the agent reads configuration (markdown, JSON, TOML, etc.)

Implementation Steps

1. Create Adapter Directory and File

Use the template at .claude/skills/new-adapter/templates/adapter.ts.

Review existing adapters for reference:

  • claude-code/adapter.ts — runtime enforcement with hook scripts
  • cursor/adapter.ts — advisory with .cursorrules + .mdc files
  • codex/adapter.ts — advisory with AGENTS.md
  • opencode/adapter.ts — advisory with instructions.md

2. Update Type Definitions

In src/types.ts, add the new agent to AgentType:

export type AgentType = 'claude-code' | 'cursor' | 'codex' | 'opencode' | '<agent-id>';

3. Update Config Schema

In src/config/schema.ts, add the agent to the Zod enum.

4. Register in CLI

In src/cli/commands/generate.ts and src/cli/commands/init.ts, add the adapter import and generation call.

5. Create Tests

Create tests/adapters/<agent-id>.test.ts with tests for:

  • Correct file generation
  • Proper merge strategy
  • All active rules included in output
  • Correct formatting for the agent's config format

6. Verify

npm run type-check
npm test -- --reporter verbose tests/adapters/<agent-id>.test.ts
npm test

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.