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.
npx agentmods add skills/mduffy37/claudeworks/create-teamnpx skills add Mduffy37/claudeworks --skill create-teamgit clone --depth 1 https://github.com/Mduffy37/claudeworksWhat 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.
| Model | Per session | Once 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 |
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.
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
- 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-profileprompt and wait for them to create it in a parallel session, then continue. - 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.
- Draft roles and per-member instructions yourself. You have the context from the team's purpose; the user can revise afterwards in the app.
- Offer team-level overrides but default to inheriting from lead. Most teams should just inherit.
- 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
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.
- 2d ago First seen · 196 lines · 70 tokens per session scan A 370b0b4bff38
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.
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.
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…
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.
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.
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…
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.