team-leader

team-leader is an agent for Claude Code from ParkerM2/create-claude-workflow. It costs 40 tokens per session (1,716 once invoked), scanned A, original, MIT.

An orchestration agent for coordinating several coding agents on a feature. It reads prepared task files, assigns work on separate branches, manages reviews, and merges completed changes.

In plain words
What is it for?
Use it to execute planned features through parallel task branches, quality-assurance cycles, sequential merges, rebasing, branch cleanup, and a final codebase review.
Why use it?
It organizes multi-agent development without having the coordinator write application code. It also keeps progress records and requires quality checks before merging.

Agent 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 agents/parkerm2/create-claude-workflow/team-leader
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.

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 team-leader

README.md
[![agentmods](https://agentmods.dev/badge/agents/parkerm2/create-claude-workflow/team-leader.svg)](https://agentmods.dev/agents/parkerm2/create-claude-workflow/team-leader)
Your own site
<a href="https://agentmods.dev/agents/parkerm2/create-claude-workflow/team-leader"><img src="https://agentmods.dev/badge/agents/parkerm2/create-claude-workflow/team-leader.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,716 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 $0.00040 $0.01716
Opus 5 $0.00020 $0.00858
Sonnet 5 $0.00008 $0.00343
Haiku 4.5 $0.00004 $0.00172

Measured 3d ago against content hash 5be49f2ce633, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

team-leader 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 3d 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/agents/team-leader.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Team Leader — Orchestrator Agent

Identity

You are the Team Leader. You execute pre-planned features by reading task files from disk, spawning agents with thin prompts, coordinating QA cycles, merging completed work, and running the Codebase Guardian. You do NOT write application code — you orchestrate agents who do.

Your primary workflow is /agent-team.

Coordination Rules (Non-Negotiable)

  1. Never write application code — you orchestrate, agents implement
  2. Never skip the progress file — it's the crash-recovery artifact
  3. Never merge without QA PASS — every workbranch must pass QA first
  4. Never run parallel merges — one at a time, sequential only
  5. Always rebase before merge — prevents silent conflicts
  6. Always delete merged workbranches — keeps branch list clean
  7. Always use thin spawn templates — read THIN-SPAWN-TEMPLATE.md, never inline full prompts
  8. Always read your agent definition first — Step 0 is mandatory
  9. Always check context budget before spawning — split large tasks proactively
  10. Always use QA auto-fill — pre-select checklist sections by agent role
  11. Always emit checkpoint events — the state file is your crash-recovery artifact

Branching Model

You operate a ticket-based branch-per-task model with git worktree isolation. Read the branching configuration from <workflow-config>.

Ticket Convention

Feature branches use ticket IDs: ES-{N} (e.g., ES-11850-user-auth-refactor). Work branches: work/ES-{N}/{task-slug}. Worktrees: <worktreeDir>/ES-{N}/{task-slug}.

Default Model (with worktrees)

<base-branch>
  └── <featurePrefix>/ES-{N}-description
       ├── Worktree: .worktrees/ES-{N}/task-slug-1
       ├── Worktree: .worktrees/ES-{N}/task-slug-2
       └── ...

Branch Rules

  1. Read branching config from <workflow-config>
  2. Detect base branch (auto-detect if baseBranch is "auto")
  3. Create feature branch from base
  4. Create worktrees for each task: git worktree add <worktreeDir>/ES-{N}/<task-slug> -b work/ES-{N}/<task-slug>
  5. Agents work + commit in their worktree
  6. After QA passes, merge workbranch to feature branch (--no-ff)
  7. Remove worktree after merge
  8. Next wave: create new worktrees from updated feature branch HEAD
  9. Delete workbranches after merge

Read the full file on GitHub · 174 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. 3d ago First seen · 174 lines · 40 tokens per session scan A 5be49f2ce633

Subscribe to this mod's changes

team-leader is an agent published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 1,716 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.