Provides 7 agents for git commits, build verification, code reviews, debugging, TDD testing with jest, project orchestration, and documentation. Auto-activates on task triggers like 'error' or 'write tests'.
From evolv3ainpx claudepluginhub evolv3ai/claude-skills-archive --plugin projectThis skill uses the workspace's default tool permissions.
README.mdagents/build-verifier.mdagents/code-reviewer.mdagents/commit-helper.mdagents/debugger.mdagents/documentation-expert.mdagents/orchestrator.mdagents/test-runner.mdrules/agent-first-thinking.mdGuides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Executes pre-written implementation plans: critically reviews, follows bite-sized steps exactly, runs verifications, tracks progress with checkpoints, uses git worktrees, stops on blockers.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
A collection of essential development workflow agents that integrate seamlessly with Claude Code.
| Agent | Purpose | Triggers On |
|---|---|---|
| commit-helper | Generate conventional commit messages | "commit message", "staged changes" |
| build-verifier | Verify dist/ matches source after builds | "changes not appearing", "verify build" |
| code-reviewer | Security audits and code quality reviews | "code review", "security audit", "OWASP" |
| debugger | Systematic debugging with root cause analysis | "error", "TypeError", "stack trace", "bug" |
| test-runner | TDD workflow and test creation | "write tests", "TDD", "coverage", "jest" |
| orchestrator | Coordinate complex multi-step projects | "coordinate", "multi-step", "complex feature" |
| documentation-expert | README, API docs, architecture diagrams | "document", "README", "API docs" |
| Rule | Purpose |
|---|---|
| agent-first-thinking | Behavioral interrupt - consider agents before manual work |
# Via marketplace
/plugin install developer-toolbox
# Or local development
/plugin install ./skills/developer-toolbox
After installation, restart Claude Code to load the agents.
"Help me write a commit message for these staged changes"
"My changes aren't appearing in production, verify the build output"
"Review this authentication code for security vulnerabilities"
"I'm getting TypeError: Cannot read property 'map' of undefined"
"Use TDD to implement this user validation function"
"Coordinate a refactor of the authentication system across 5 services"
"Create comprehensive API documentation for this REST endpoint"
All agents follow the "MUST BE USED when" pattern for reliable auto-discovery:
description: |
[Role] specialist. MUST BE USED when: [trigger 1], [trigger 2], [trigger 3].
Use PROACTIVELY for [broad task category].
Keywords: keyword1, keyword2, error-message-fragment
This ensures Claude Code discovers and proposes the right agent automatically based on user requests.
The included agent-first-thinking.md rule encourages using agents by default:
The Inversion:
Triggers:
| If about to... | Use instead... |
|---|---|
| grep/glob 3+ times | Explore agent |
| Read 5+ files | Explore agent |
| Same edit across files | Parallel agents |
| Audit multiple items | Parallel swarm |
Each agent can be extended by editing its markdown file after installation:
# Find installed agents
ls ~/.claude/plugins/cache/*/developer-toolbox/*/agents/
# Or copy to user-level for customization
cp [plugin-path]/agents/code-reviewer.md ~/.claude/agents/
Agents work well together:
"Review this code for security issues, then write tests for the critical paths"
# → code-reviewer first, then test-runner
"Debug this failing test, document the root cause, and commit the fix"
# → debugger → documentation-expert → commit-helper