Expert architecture review and system design for problems spanning 2+ files or crossing module boundaries — circular dependencies, God modules, or boundary violations (bleed). Not for single-file cleanup (see refactor). Trigger on: 'architecture review', 'restructure across modules', 'too coupled', 'design this system', 'where should this code live', 'God class', 'circular deps', 'dependency mapping', 'domain boundaries'.
Structured discovery to prevent rework. Use for new product features or ambiguous requirements. Trigger on: 'let's build a feature', 'new feature', 'I want to implement', 'add X to', 'ambiguous design', 'unclear terminology', 'requirements discovery', 'brainstorming', 'stakeholder probe', 'glossary definition'.
Initialize or audit repository instructions. Generates high-signal AGENTS.md wired to CLAUDE.md/GEMINI.md stubs. Not for documenting a specific feature's spec or design (see planning, brainstorming). Trigger on: 'init codebase', 'onboard repo', 'audit AGENTS.md', 'setup agent instructions', 'codebase-init', 'initialize project memory'.
Disciplined root-cause analysis for bugs and crashes. Systematic falsification workflow to identify true causes. Not for writing tests for new feature work (see test-driven-development) or non-bug structural cleanup (see refactor). Trigger on: 'debug', 'fix crash', 'why is this failing', 'unexpected output', 'diagnose bug', 'root cause analysis', 'feedback loop', 'instrumentation'.
Secure GitHub automation and CLI scripting. Expert in GitHub Actions, OIDC, and SHA-pinning. Not for reviewing code quality or correctness (see request-code-review). Trigger on: 'add CI', 'setup release', 'harden workflow', 'gh api', 'github-automation', 'least-privilege permissions', 'OIDC setup'.
Matches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
Verified owner:Linus Johansson
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
External network access
Connects to servers outside your machine
External network access
Connects to servers outside your machine
A Claude Code plugin for authoring and maintaining skills and hooks — structured workflows and lifecycle hooks that guide Claude through the full agent development lifecycle.
Agent Dev Plugin extends Claude Code with 13 skills and 3 lifecycle hooks covering the complete agent development cycle. Skills activate automatically based on task context and can also be invoked manually; hooks fire on session events to guard against destructive commands, surface relevant skills, and keep a local telemetry trail. Multi-step or parallel work is delegated to the built-in general-purpose agent — configured per task via the prompt — orchestrated by the multi-agent-dispatch (parallel fan-out) and multi-agent-development (sequential, gate-checked) skills.
| Aspect | Detail |
|---|---|
| Status | Stable — v1.0.0 |
| Language | JavaScript (ESM) · Python |
| Runtime | Node.js ≥ 22 · Python ≥ 3.10 |
| Package manager | npm |
| License | MIT |
| Feature | Description |
|---|---|
| 13 auto-triggered skills | Activate on task context; invoke manually with /skill-name |
| Subagent orchestration | multi-agent-dispatch and multi-agent-development drive every general-purpose subagent dispatch — no custom agent definitions to maintain |
| 3 lifecycle hooks | Bash-only handlers: a shell-safety guard, a skill nudge, and telemetry capture |
| Marketplace install | One-command install from GitHub — no manual clone required |
[!TIP] Marketplace install is recommended — upgrades are handled automatically.
.claude/settings.json:{
"extraKnownMarketplaces": {
"claude-agent-dev": {
"source": {
"source": "github",
"repo": "j0hanz/claude-agent-dev-plugin"
}
}
}
}
claude plugin install claude-agent-dev@claude-agent-dev
git clone https://github.com/j0hanz/claude-agent-dev-plugin.git
claude --plugin-dir ./claude-agent-dev-plugin
| Requirement | Version / Notes |
|---|---|
| Node.js | ≥ 22 |
| Python | ≥ 3.10 |
| Claude Code | latest |
| Python packages | pip install pytest pyyaml jsonschema |
Skills are invoked automatically by Claude based on task context, or manually with /skill-name.
npx claudepluginhub j0hanz/claude-agent-dev-pluginComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.