Project: claude-agents

Project: claude-agents

Claude Code plugin marketplace — 72 focused plugins, 112 agents, 146 skills, 79 tools.

Repository Structure

claude-agents/
├── .claude-plugin/marketplace.json   # Registry of all plugins
├── plugins/                          # All 72 plugins
│   ├── /
│   │   ├── .claude-plugin/plugin.json
│   │   ├── agents/*.md
│   │   ├── commands/*.md
│   │   └── skills//SKILL.md
│   └── ...
├── docs/                             # Documentation
│   ├── plugins.md                    # Plugin catalog
│   ├── agents.md                     # Agent reference
│   ├── agent-skills.md               # Skills reference
│   ├── usage.md                      # Usage guide
│   ├── architecture.md               # Design principles
│   └── plugin-eval.md                # Evaluation framework
└── tools/                            # Development utilities

Plugin Authoring Conventions

Agent frontmatter

---
name: agent-name
description: "What this agent does. Use PROACTIVELY when [trigger conditions]."
model: opus|sonnet|haiku|inherit
color: blue|green|red|yellow|cyan|magenta # optional
tools: Read, Grep, Glob # optional — restricts available tools
---

Skill structure

skills//
├── SKILL.md              # Required — frontmatter + content
├── references/           # Optional — supporting material
│   └── *.md
└── assets/               # Optional — templates, configs

Skill frontmatter:

---
name: skill-name
description: "Use this skill when [specific trigger conditions]."
---

Command frontmatter

---
description: What this command does
argument-hint:  [--flag]
---

plugin.json

Only `name` is required. Agents, commands, and skills are auto-discovered from directory structure.

{ "name": "plugin-name" }

marketplace.json

Lists all plugin component paths for the registry. Agents as `./agents/name.md`, skills as `./skills/skill-name` (directory, not SKILL.md).

Model Tiers

Tier	Model	Use Case
Tier 1	Opus	Architecture, security, code review, production coding
Tier 2	Inherit	Complex tasks — user chooses model
Tier 3	Sonnet	Docs, testing, debugging, support
Tier 4	Haiku	Fast ops, SEO, deployment, simple tasks

PluginEval — Quality Evaluation Framework

Three-layer evaluation system in `plugins/plugin-eval/`. Full docs: [docs/plugin-eval.md](docs/plugin-eval.md).

Quick Reference

cd plugins/plugin-eval

# Run tests
uv run pytest

# Evaluate a skill (static only)
uv run plugin-eval score path/to/skill --depth quick --output json

# Evaluate with LLM judge
uv run plugin-eval score path/to/skill --depth standard

# Full certification (all 3 layers)
uv run plugin-eval certify path/