create-team

A guided setup for a ClaudeWorks team, where several existing Claude Code profiles work together on one task under a lead profile.

In plain words
What is it for?
Use it to describe a team’s purpose, select its members and lead, draft their roles, and produce prompts for creating missing profiles.
Why use it?
It helps turn a broad team idea into coordinated member roles and instructions, while showing which profiles are missing.

Skill for Claude CodeCodex

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/mduffy37/claudeworks/create-team
Any agent
npx skills add Mduffy37/claudeworks --skill create-team
Clone the repo
git clone --depth 1 https://github.com/Mduffy37/claudeworks

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,914 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 $0.00070 $0.02914
Opus 5 $0.00035 $0.01457
Sonnet 5 $0.00014 $0.00583
Haiku 4.5 $0.00007 $0.00291

Measured 2d ago against content hash 370b0b4bff38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-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.

src/builtin-plugin/skills/create-team/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are creating a new ClaudeWorks team. A team is a composition of profiles that launch together as a coordinated multi-agent session, with one profile as the lead.

Design contract

  1. Team members reference existing profiles only. The team itself never creates profiles. When the user's description needs a profile that doesn't exist, you hand them a paste-ready /create-profile prompt and wait for them to create it in a parallel session, then continue.
  2. Prefer orchestrator-style profiles as lead. The lead profile drives merged config (model, effort, plugins, MCP servers) for the whole team — it should be the one best-suited to coordinating, synthesizing, and tracking parallel work.
  3. Draft roles and per-member instructions yourself. You have the context from the team's purpose; the user can revise afterwards in the app.
  4. Offer team-level overrides but default to inheriting from lead. Most teams should just inherit.
  5. Stay resident across turns. You do not end the conversation until the team is either written or explicitly abandoned.

Step 1 — Ask the purpose

Ask one short question: "What is this team for?" Accept a free-form description (e.g. "code review panel", "frontend feature development", "incident triage", "research squad for weekly papers"). Do not batch multiple questions at this step — purpose first, composition later.

Step 2 — Read state

Always read both profiles and existing teams. The team design depends on what's available to compose from, and team names must be unique.

!node -e " const fs=require('fs'),path=require('path'),os=require('os'); const pfPath=path.join(os.homedir(),'.claudeworks','profiles.json'); const tmPath=path.join(os.homedir(),'.claudeworks','teams.json'); const store=fs.existsSync(pfPath)?JSON.parse(fs.readFileSync(pfPath,'utf-8')):{profiles:{}}; const teams=fs.existsSync(tmPath)?JSON.parse(fs.readFileSync(tmPath,'utf-8')):{teams:{}}; const list=Object.values(store.profiles||{}).map(p=>({ name:p.name, description:p.description||'', plugins:(p.plugins||[]).length, pluginIds:(p.plugins||[]).slice(0,6), model:p.model||'(global default)', effort:p.effortLevel||'(global default)', tags:p.tags||[], hasWorkflow:!!(p.workflow&&p.workflow.trim()), lastLaunched:p.lastLaunched||0, isDefault:!!p.isDefault, })); console.log(JSON.stringify({profiles:list,existingTeams:Object.keys(teams.teams||{})},null,2)); " 2>&1

Read the full file on GitHub · 196 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 · 196 lines · 70 tokens per session scan A 370b0b4bff38

Subscribe to this mod's changes

create-team is a skill published in the GitHub repository Mduffy37/claudeworks (11 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 2,914 once invoked, about $0.0003 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

snip

You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.

edouard-claude/snip · 0 tokens

todos

This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…

JetBrains/thinkrail · 127 tokens

writing-workflow-skills

Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.

JetBrains/thinkrail · 60 tokens

reviewing-changes

Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.

JetBrains/thinkrail · 59 tokens

setting-up-a-project

Use whenever asked to set up, onboard, initialize, or spec a project — the front door when the workspace has no spec graph yet (brand-new or an existing codebase); also seeded by the app's Set-up-project card (/skill:setting-up-a-project). Not for feature work in an already-specced project — use the brainstorming…

JetBrains/thinkrail · 76 tokens

writing-specs

Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.

JetBrains/thinkrail · 59 tokens