Borrowing it
Nothing to install: this file belongs to changoo89/claude-pilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/changoo89/claude-pilot/main/.claude/skills/agent-teams/SKILL.mdgit clone --depth 1 https://github.com/changoo89/claude-pilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/changoo89/claude-pilot/agent-teams)<a href="https://agentmods.dev/skills/changoo89/claude-pilot/agent-teams"><img src="https://agentmods.dev/badge/skills/changoo89/claude-pilot/agent-teams/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/changoo89/claude-pilot/agent-teams"><img src="https://agentmods.dev/badge/skills/changoo89/claude-pilot/agent-teams.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.01341 |
| Opus 5 | $0.00015 | $0.00671 |
| Sonnet 5 | $0.00006 | $0.00268 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
agent-teams scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Agent Teams
Purpose: Native Claude Code Agent Teams coordination with team templates and quality gates Target: Team Leads coordinating execution-team, review-team, planning-team
Quick Start
When to Use
- Execute SCs with specialized agents (coder, frontend-engineer, backend-engineer)
- Multi-angle review with cross-discussion
- Parallel exploration and research
Quick Reference
# Spawn teammate for SC implementation
Spawn teammate "sc1-impl" with prompt:
"You are a coder (see @.claude/agents/coder.md).
Execute SC-1 from $PLAN_PATH. Skills: tdd, ralph-loop, vibe-coding.
When complete, mark task as done. If blocked, message the team lead."
# Delegate mode (Shift+Tab): coordinate only, never implement
# TaskCompleted hook auto-verifies tests/coverage/todos
What This Skill Covers
In Scope
- Agent Teams coordination patterns
- Team templates (execution, review, planning)
- Teammate spawning with role-specific prompts
- TaskCompleted and TeammateIdle hook integration
Out of Scope
- Hook implementation details → @.claude/hooks/verify-task-completion.sh
- Individual agent definitions → @.claude/agents/
- Test frameworks and coverage → @.claude/skills/tdd/SKILL.md
Core Concepts
Architecture
- Team Lead: Coordinates in delegate mode (Shift+Tab), never implements directly
- Teammates: Independent agents, full context, direct communication, shared Task List
- Quality Gates: TaskCompleted hook (auto-verify), TeammateIdle hook (prevent premature idle)
- Communication: Multi-directional (teammate ↔ teammate ↔ lead)
Delegate Mode (MANDATORY)
Team Lead MUST coordinate only (spawn teammates, monitor, aggregate) and NEVER implement (edit files, write tests).
Pattern: Spawn → Monitor → Handle messages → Aggregate
Team Templates
- execution-team: SC implementation (coder, frontend-engineer, backend-engineer)
- review-team: Multi-angle review (tester, validator, code-reviewer, security-analyst)
- planning-team: Exploration/research (explorer, researcher)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 159 lines · 31 tokens per session scan A 21320c2240c1
agent-teams is a skill published in the GitHub repository changoo89/claude-pilot (20 stars, last pushed 7mo ago), licensed MIT. It adds 31 tokens to every session and 1,341 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
frontend-code-review
Trigger when the user requests a review of frontend files (e.g., .tsx, .ts, .js). Support both pending-change reviews and focused file reviews while applying the checklist rules.
generic-react-code-reviewer
Review React/TypeScript code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Enforces TypeScript strict mode, GPU-accelerated animations, WCAG AA accessibility, bundle size limits, and surgical simplicity. Use when completing features, before commits, or…
ocr
AI-powered multi-agent code review. Simulates a team of Principal Engineers reviewing code from different perspectives. Use when asked to review code, check a PR, analyze changes, or perform code review.
generic-fullstack-code-reviewer
Review full-stack code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md compliance. Enforces TypeScript strict mode, input validation, GPU-accelerated animations, and design system consistency. Use when completing features, before commits, or reviewing pull requests.