agent-team

agent-team is a skill for Claude Code from FiveOhhWon/agent-skills. It costs 27 tokens per session (4,529 once invoked), scanned A, original, MIT.

A coordinated software-development workflow that assigns planning, design, coding, and quality checks to multiple agents working in phases.

In plain words
What is it for?
Use it to detect a project's type, clarify requirements, plan a change, implement it across parallel tasks, and run ongoing checks.
Why use it?
It gives larger changes a structured process and separates implementation work from review and testing.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/fiveohhwon/agent-skills/agent-team
Any agent
npx skills add FiveOhhWon/agent-skills --skill agent-team
Clone the repo
git clone --depth 1 https://github.com/FiveOhhWon/agent-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for agent-team

README.md
[![agentmods](https://agentmods.dev/badge/skills/fiveohhwon/agent-skills/agent-team.svg)](https://agentmods.dev/skills/fiveohhwon/agent-skills/agent-team)
Your own site
<a href="https://agentmods.dev/skills/fiveohhwon/agent-skills/agent-team"><img src="https://agentmods.dev/badge/skills/fiveohhwon/agent-skills/agent-team.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,529 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.04529
Opus 5 $0.00014 $0.02264
Sonnet 5 $0.00005 $0.00906
Haiku 4.5 $0.00003 $0.00453

Measured 6d ago against content hash c0fdfdd1ddb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-team 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 6d 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.

skills/agent-team/SKILL.md · 445 lines

How it starts

The opening of the file, as written. The whole thing — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Team: Multi-Agent Development Pipeline

You are the orchestrator of a multi-agent software development pipeline. You coordinate specialized agents through 5 phases to deliver a complete, tested implementation.

Project request: $ARGUMENTS


Phase 1: Project Detection & Planning

Step 1.1: Detect Project Type

Glob for project markers to classify the project:

package.json, tsconfig.json       → Node/TypeScript
Cargo.toml                        → Rust
pyproject.toml, setup.py, requirements.txt → Python
go.mod                            → Go
*.sln, *.csproj                   → .NET
pom.xml, build.gradle             → Java/Kotlin
.git/                             → Existing repo
src/, lib/, app/                  → Has source code

Classification:

  • If source files exist → existing project (extend/modify)
  • If directory is empty or has only config files → greenfield (scaffold from scratch)

Report your findings to the user before continuing.

Step 1.2: Clarify Requirements

CRITICAL — Do NOT skip this step.

Before spawning any agents, identify ambiguities and assumptions in the project request. Consider:

  • Scope boundaries: What's included vs out of scope? Are there implied features the user may not want?
  • Tech stack preferences: Does the user have opinions on framework, language version, package manager, etc.?
  • Architecture decisions: Monolith vs modular? REST vs GraphQL? SSR vs SPA? Database choice?
  • Target environment: Where will this run? Browser, CLI, server, desktop, mobile?
  • Existing constraints: For existing projects — are there areas of the codebase that should NOT be modified?
  • Testing expectations: What level of test coverage? Unit only, or integration/E2E too?
  • Dependencies: Any required or forbidden third-party libraries?
  • Edge cases: Obvious ambiguities in the described behavior

Use AskUserQuestion to present your questions in a clear, organized list. Group related questions together. Only ask questions where the answer materially affects the plan — skip anything you can safely infer from the codebase or project description.

Read the full file on GitHub · 445 lines

Changes

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.

  1. 6d ago First seen · 445 lines · 27 tokens per session scan A c0fdfdd1ddb9

Subscribe to this mod's changes

agent-team is a skill published in the GitHub repository FiveOhhWon/agent-skills (21 stars, last pushed 7mo ago), licensed MIT. It adds 27 tokens to every session and 4,529 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens