Orchestrate specialist agents to execute implementation plans, with pre-flight validation.
Language-agnostic code reviewer. Use as fallback when no language-specific reviewer (java-code-reviewer, python-code-reviewer, node-code-reviewer) is available. Covers universal concerns across any stack.
Language-agnostic security auditor. Use as fallback when no stack-specific security auditor is available. Covers OWASP Top 10, secret leakage, auth/authz issues, input validation, common injection vectors.
Use after preflight-check passes to parse an implementation plan and propose a team roster. Detects tech stack from file paths, matches each domain to the best specialist agent.
Use when validating an implementation plan before launching a team via /team-building. Runs plan quality, project readiness, and team hygiene checks. Auto-repairs safe issues, asks for risky ones, blocks on critical failures.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin that turns an implementation plan into a coordinated team of specialist agents — with pre-flight validation, parallel execution, mandatory code review, and a security audit.
You write the plan. The plugin assembles the right agents for the stack, runs them as a real Team (using Claude Code's Team Agents feature so they share task state and can message each other), and gates everything behind a quality check that runs before any code gets written.
| Component | Type | Purpose |
|---|---|---|
/team-building | Command | Entry point. Reads a plan, runs preflight, builds the team, executes, reviews. |
preflight-check | Skill | Plan-quality + project-readiness gatekeeper. Auto-repairs safe issues, blocks on critical failures. |
plan-analysis | Skill | Detects tech stack from the plan, matches each task to the best specialist agent available. |
generic-code-reviewer | Agent | Language-agnostic code reviewer. Bundled fallback when no stack-specific reviewer is installed. |
generic-security-auditor | Agent | Language-agnostic security auditor. Bundled fallback. Covers OWASP Top 10. |
The two pinned review agents are language-agnostic on purpose so the plugin works out-of-the-box on any project. If you have stack-specific reviewers (java-code-reviewer, python-code-reviewer, node-code-reviewer, etc.) installed, the plugin prefers those automatically.
Inside Claude Code, run:
/plugin marketplace add pablomarotta4/team-building
/plugin install team-building@team-building-marketplace
That's it. The /team-building command is now available, the two skills are registered, and the two fallback agents are discoverable.
To verify:
/plugin
You should see team-building listed as an installed plugin.
When the repo changes upstream, refresh with:
/plugin marketplace update pablomarotta4/team-building
Then /plugin reload (or restart your session) to pick up the new version.
/plugin uninstall team-building
/plugin marketplace remove team-building-marketplace
docs/plans/<date>-<feature>.md. The writing-plans skill (or superpowers:writing-plans) is a good way to produce one./team-building docs/plans/2026-04-09-payment-webhook.md
preflight-check. If it returns BLOCK, you'll see the failures and the team is not assembled. If WARN, it'll surface issues and ask you whether to proceed. If PASS, it moves on.plan-analysis. Detects the stack, classifies each task, proposes a team roster (specialists + the two pinned review agents).TeamCreate and dispatch tasks. Specialists work in parallel where possible, with explicit file-ownership boundaries to avoid conflicts./team-building docs/plans/myplan.md --skip-checks
This downgrades CRITICAL failures to warnings and proceeds. Use rarely — preflight catches real problems.
Open commands/team-building.md (in the installed plugin folder or in this repo if you forked it) and edit the Pinned Agents table. Remove rows to drop an agent from the Review phase, or add new ones to force-include them. Common customizations:
pr-test-analyzer row to require test-coverage review on every team run.generic-code-reviewer out for a stricter house reviewer.comment-analyzer row to enforce documentation hygiene.TeamCreate / TaskCreate / Agent(team_name=...) / SendMessage for coordination.team-building/
├── .claude-plugin/
│ ├── plugin.json # plugin manifest
│ └── marketplace.json # marketplace manifest (source: "./")
├── agents/
│ ├── generic-code-reviewer.md
│ └── generic-security-auditor.md
├── commands/
│ └── team-building.md # the /team-building command
└── skills/
├── plan-analysis/
│ ├── SKILL.md
│ └── references/
└── preflight-check/
├── SKILL.md
└── references/
npx claudepluginhub pablomarotta4/team-building --plugin team-buildingUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Comprehensive 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.