Team Lead Orchestration

Team Lead Orchestration is a skill for Claude Code from ChrisMckerracher/claude-dream-team. It costs 45 tokens per session (1,006 once invoked), scanned A, original, MIT.

A guide for coordinating several coding agents on a large project. It explains how to split work into dependent tasks, where a DAG means a task map with no circular dependencies, and how to assign agents to each part.

In plain words
What is it for?
Use it to plan epics, choose and start teams of agents, divide work into tasks, coordinate implementation and testing, and handle escalations.
Why use it?
It helps organize complex work when tasks must happen in a particular order or different agents need to collaborate.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the dream-team plugin — 11 skills, 3 hooks shipped together

Good fit Use it to plan epics, choose and start teams of agents, divide work into tasks, coordinate implementation and testing, and handle escalations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chrismckerracher/claude-dream-team/team-lead
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.

Any agent
npx skills add ChrisMckerracher/claude-dream-team --skill team-lead
Clone the repo
git clone --depth 1 https://github.com/ChrisMckerracher/claude-dream-team

Made for: Claude Code.

Or install dream-team, the plugin that ships this one along with the rest of its 11 skills, 3 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 Lead Orchestration

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrismckerracher/claude-dream-team/team-lead/github.svg)](https://agentmods.dev/skills/chrismckerracher/claude-dream-team/team-lead)
Your own site
<a href="https://agentmods.dev/skills/chrismckerracher/claude-dream-team/team-lead"><img src="https://agentmods.dev/badge/skills/chrismckerracher/claude-dream-team/team-lead/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.

agentmods 80×15 button for Team Lead Orchestration

Your own site · 80×15
<a href="https://agentmods.dev/skills/chrismckerracher/claude-dream-team/team-lead"><img src="https://agentmods.dev/badge/skills/chrismckerracher/claude-dream-team/team-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,006 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00045 $0.01006
Opus 5 $0.00023 $0.00503
Sonnet 5 $0.00009 $0.00201
Haiku 4.5 $0.00005 $0.00101

Measured 12d ago against content hash cf43f841df4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Team Lead Orchestration 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 12d 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.

dream-team-plugin/skills/team-lead/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Team Lead Orchestration Skill

Team Spawning Templates

Epic Planning Team

Spawn order:
1. Product Agent - for feature files and briefs
2. Architect Agent - for technical design docs
(These can run in parallel if the epic is well-defined)

Epic Execution Team

Spawn order:
1. Code Review Agent (1) - monitors review queue
2. QA Agent (1) - validates against product specs
3. Coding Agent(s) (1-3) - implement tasks in worktrees
Optional:
4. UI/UX Designer (1) - if epic involves UI work

Bug Investigation Team

Spawn per-lead:
- Coding Agent OR QA Agent per investigation lead
- Team Lead delegates all investigation — never analyzes code directly
(best judgment based on nature of the lead)

Task Decomposition as DAG

When decomposing an epic into tasks, structure as a Directed Acyclic Graph:

Example DAG:
  [DB Schema Migration] ──┐
                          ├──> [API Endpoints] ──┐
  [Type Definitions] ─────┘                      ├──> [Integration Tests]
                                                 │
  [UI Components] ─────> [UI Integration] ───────┘

Decomposition Rules

  1. Each task should be < 500 lines of change (target)
  2. Tasks that can run in parallel should have no dependency edges
  3. Tests should be bundled with their implementation task
  4. Integration tests may be a final leaf task - that's acceptable
  5. Every task needs clear acceptance criteria
  6. Mark which tasks require specific agent types

Task Metadata Template

Task: [Short title]
Depends on: [task IDs]
Agent type: coding | qa | design
Acceptance criteria:
  - [ ] Criterion 1
  - [ ] Criterion 2
Estimated scope: small (<100 LOC) | medium (100-300 LOC) | large (300-500 LOC)

Workflow State Machine

PLANNING
  ├── Product + Architect working (parallel or sequential)
  ├── Review docs
  ├── Iterate if needed
  └── Approve → DECOMPOSITION

DECOMPOSITION
  ├── Break into task DAG
  ├── User review (blocker)
  └── Approve → EXECUTION

EXECUTION
  ├── Coding agents implement
  ├── Code Review gates
  ├── QA validation
  ├── Critical error? → PLANNING (partial)
  └── dtq status shows ALL items merge-ready → VALIDATION
      (do NOT proceed while any items are in review/qa/coding)

VALIDATION
  ├── Full feature flow testing
  ├── Broken flows? → EXECUTION (new tasks)
  └── All passing → COMPLETE

Read the full file on GitHub · 136 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. 12d ago First seen · 136 lines · 45 tokens per session scan A cf43f841df4d

Subscribe to this mod's changes

Team Lead Orchestration is a skill published in the GitHub repository ChrisMckerracher/claude-dream-team (5 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 1,006 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.

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

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

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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens