agent-team

A command for carrying out a feature plan with several cooperating coding agents. It reads prepared task files and runs the work through required setup, execution, and verification stages.

In plain words
What is it for?
Use it when a feature has already been broken into tasks and needs coordinated implementation across separate work areas.
Why use it?
It keeps multi-agent work in a defined order and checks that each stage is ready before the next begins.

Command for Claude Code

Part of the claude-workflow plugin — 10 skills, 25 commands, 3 agents, 6 hooks shipped together

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 commands/parkerm2/create-claude-workflow/agent-team
Clone the repo
git clone --depth 1 https://github.com/ParkerM2/create-claude-workflow

Made for: Claude Code.

Or install claude-workflow, the plugin that ships this one along with the rest of its 10 skills, 25 commands, 3 agents, 6 hooks.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 588 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 $0.00033 $0.00588
Opus 5 $0.00016 $0.00294
Sonnet 5 $0.00007 $0.00118
Haiku 4.5 $0.00003 $0.00059

Measured 2d ago against content hash 7915f77aee17, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

.claude/commands/agent-team.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/agent-team — Execute Pre-Planned Feature


How This Works

Each step below is a skill invocation. The skill loads its own focused instructions when you call it. You follow those instructions, complete them, then return here and check the box before moving to the next step.

Rules:

  • Invoke each skill with the Skill tool before doing anything else in that step
  • Do NOT read agents/team-leader.md or any prompts/implementing-features/*.md directly
  • Each skill verifies the previous step completed — if a gate fails, fix it before continuing
  • Do NOT skip steps, combine steps, or substitute your own instructions

Execution Checklist

  • Step 1 — Pre-flight Skill("claude-workflow:wf-preflight") Verifies infrastructure, git state, config, and task files. Writes the preflight stamp.

  • Step 2 — Load Plan Skill("claude-workflow:wf-plan") Reads task files, validates structure, builds wave plan. Requires preflight stamp.

  • Step 3 — Team Setup Skill("claude-workflow:wf-setup") TeamCreate, runtime values injected into task files, worktrees created, CLAUDE.md injected per worktree. Requires plan stamp.

  • Step 4 — Execute Waves (repeat for each wave)

    • Skill("claude-workflow:wf-spawn") Spawns coder + QA pair for each task in current wave.
    • Skill("claude-workflow:wf-qa-gate") Waits for verdicts, handles QA cycles, merges passing tasks. Repeat Steps 4a–4b until all waves complete.
  • Step 5 — Guardian Skill("claude-workflow:wf-guardian") Structural integrity check on the feature branch. Requires all-waves-complete stamp.

  • Step 6 — Finalize Skill("claude-workflow:wf-finalize") Shutdown agents, cleanup worktrees, push branch, create PR, report to user. Requires guardian-passed stamp.

Read the full file on GitHub · 63 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. 2d ago First seen · 63 lines · 33 tokens per session scan A 7915f77aee17

Subscribe to this mod's changes

agent-team is a command published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 588 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 2026-08-31.