team

A planning guide for deciding whether a large coding task should be split among several AI workers. It considers task size, roles, dependencies, and safe parallel work.

In plain words
What is it for?
Use it to assess large tasks, choose suitable roles, map dependencies, decide how many workers to use, and plan how they finish their work.
Why use it?
It helps avoid assigning small tasks to a team or starting parallel work when one task depends on another. This makes the allocation decision clearer before work begins.

Skill for Claude CodeCodex

Part of the autopilot plugin — 32 skills, 3 agents, 7 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 skills/cookys/autopilot/team
Any agent
npx skills add cookys/autopilot --skill team
Clone the repo
git clone --depth 1 https://github.com/cookys/autopilot

Made for: Claude Code, Codex.

Or install autopilot, the plugin that ships this one along with the rest of its 32 skills, 3 agents, 7 hooks.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,433 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00039 $0.01433
Opus 5 $0.00019 $0.00717
Sonnet 5 $0.00008 $0.00287
Haiku 4.5 $0.00004 $0.00143

Measured 3d ago against content hash fa63265e86c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

team scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

!`cat .claude/team-config.md 2>/dev/null || echo "_No config — using generic role templates below._"`
platforms/codex/plugin/skills/team/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Team Allocation

Coexistence with Superpowers

This skill is autopilot's standalone methodology for team allocation decisions — when to organize parallel work, which roles to assign, how to analyze dependencies. If the superpowers plugin is installed, superpowers:dispatching-parallel-agents is the dispatch mechanism (the verb), but role/dependency planning (the noun) is still this skill's domain.

Differences worth knowing:

  • autopilot:team = allocation decision tree (when to組隊, role 選擇, 依賴分析, team size rules, shutdown flow).
  • superpowers:dispatching-parallel-agents = the technical dispatch mechanism — issuing parallel agent calls with structured reporting.
  • For the dispatch mechanism preference (after allocation decided), see .claude/dispatch-config.md's ## Parallel Dispatch chain. For allocation methodology, this skill is the primary entry point regardless.

Project Config (auto-injected)

!cat .claude/team-config.md 2>/dev/null || echo "_No config — using generic role templates below._"

When Teams Are Needed

Size Team Action
S No Do directly
L Evaluate Use decision tree below

Decision Tree

L-size task
├── All phases sequentially dependent? → No team, solo by phase
├── 2+ independent parallel work blocks? → Build team
│   ├── Backend + Frontend changes   → backend-dev + frontend-dev
│   ├── Audit then implement         → auditor + implementer
│   ├── Multiple modules each need changes → per-module agents
│   └── Research + implement can overlap   → researcher + implementer
└── Unsure? → Solo Phase 0 design first, then decide

Role Templates

Role subagent_type Use Case
backend-dev general-purpose Backend/server changes
frontend-dev general-purpose Frontend/client changes
auditor Explore Code audit, investigation
researcher Explore Architecture research, comparison
tester general-purpose E2E/stress testing

Read the full file on GitHub · 150 lines

Files

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.

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 · 150 lines · 39 tokens per session scan B fa63265e86c5

Subscribe to this mod's changes

team is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 1,433 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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