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 skills add kochetkov-ma/claude-brewcode --skill teams-setupgit clone --depth 1 https://github.com/kochetkov-ma/claude-brewcodeWrote 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.
[](https://agentmods.dev/skills/kochetkov-ma/claude-brewcode/teams-setup)<a href="https://agentmods.dev/skills/kochetkov-ma/claude-brewcode/teams-setup"><img src="https://agentmods.dev/badge/skills/kochetkov-ma/claude-brewcode/teams-setup/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.
<a href="https://agentmods.dev/skills/kochetkov-ma/claude-brewcode/teams-setup"><img src="https://agentmods.dev/badge/skills/kochetkov-ma/claude-brewcode/teams-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.02514 |
| Opus 5.5 | $0.00011 | $0.01006 |
| Sonnet 5.5 | $0.00006 | $0.00503 |
| Haiku 4.5 | $0.00003 | $0.00251 |
Grade A, and why
teams-setup 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 today.
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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex team coordination
Use collaboration agents only when the user or project instructions explicitly request a team. Split work into bounded independent tasks, keep one owner per file or surface, exchange evidence through collaboration messages, and synthesize results in the parent session. Do not invent unsupported agent parameters or create persistent team configuration unless requested.
Native authority
Manage persistent project teams under .codex/teams/{TEAM_NAME}/ and agents under .codex/agents/. Domain agents are native TOML parsed with Python tomllib, never renamed Markdown. Each has exactly the three string keys name, description, and developer_instructions; description is one nonempty line of at most 100 characters. Read applicable AGENTS.md, preserve unrelated files, use only adjacent scripts/references, and never edit installed caches.
Before every team.md write, resolve REPORT_ROOT from the narrowest applicable durable project guidance; an exact declared project-relative path wins, and guidance silence falls back to .codex/reports. Every slash-separated segment must match ^[A-Za-z0-9._-]+$ and must not equal . or ..; reject absolute/home-relative paths, doubled slashes, unresolved tokens, control characters, and shell metacharacters including $(), backticks, ;, &, and |. Equal-specificity conflicting report-root directives -> STOP instead of selecting either. Dusk guidance therefore resolves exactly .codex/reports, never a tool-default path.
Invocation and approval
Resolve exactly one mode in this order: status, install, upgrade, enable, disable, uninstall, purge. An explicit mode wins. With no mode, choose status when the named team exists; otherwise choose install and team name default only when no name was supplied. Invalid detector output stops the run.
Before any action, print one PLAN — brewcode:teams-setup block with INPUT, resolved MODE and reason, SCOPE (team, roster, exact paths), DO, and RESULT. status asks nothing. Every mutating mode requires existing authorization or explicit main-chat approval after a concrete, reviewable proposal and before the first write; changed scope requires a revised proposal and actual user reply. Destructive modes additionally name every deletion.
What ships with it
22 files 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.
- agents/openai.yaml 233 B
- LICENSE 1.1 KB
- README.md 2.8 KB
- references/agent-template.md 1.4 KB
- references/cleanup-flow.md 8.5 KB
- references/framework-files.md 4.6 KB
- scripts/agent-generator.sh 1.5 KB runs code
- scripts/agent-owners.sh 2.9 KB runs code
- scripts/count-tokens.py 2.9 KB runs code
- scripts/detect-mode.sh 4.9 KB runs code
- scripts/prepare-tokenizer.py 40 KB runs code
- scripts/scope-guard.sh 4.3 KB runs code
- scripts/toggle-team.sh 6.5 KB runs code
- scripts/trace-ops.sh 36 KB runs code
- scripts/verify-team.sh 32 KB runs code
- tests/run.sh 2.8 KB runs code
- tests/suite-agent-profile-contract.mjs 68 KB runs code
- tests/suite-intent-guard.mjs 15 KB runs code
- tests/suite-lifecycle.mjs 39 KB runs code
- tests/suite-multi-team.mjs 6.7 KB runs code
- tests/suite-parked-conflict.mjs 17 KB runs code
- tests/suite-trace-ops.mjs 66 KB runs code
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.
- today Changed 593891ce430c
- 2d ago Changed a7145f04d0dd
- 3d ago Changed 0202b9e81480
- 4d ago Changed 706fb6b45b89
- 9d ago Changed dcad83b73563
- 10d ago Changed fe341c9b424f
- 11d ago Changed c36ab5fc0625
- 12d ago Changed 8bfe57abfae7
- 13d ago Changed f7c12f026c90
- 20d ago First seen · 85 lines · 28 tokens per session scan A 3e768c47fbbb
teams-setup is a skill published in the GitHub repository kochetkov-ma/claude-brewcode (38 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 2,514 once invoked, about $0.0001 per session on Opus 5.5. 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
doc-digest
Turn a long document, PDF, transcript, spreadsheet or log into a compact working digest the conversation can continue from. Use when the user shares or pastes something long (several pages or more) and wants to discuss, analyze, compare or use it over more than one message, or asks to summarize a document so they can…
fresh-start
Continue in a new chat without losing anything — writes a compact handoff to paste into a fresh conversation. Use whenever the user wants to move to a new chat or conversation, hits usage limits, says replies got slow or Claude forgets earlier details, or the conversation has grown long.
token-check
Estimate how many tokens a pasted text, an attached file or the conversation so far takes, what it means for the context window and usage limits, and how to cut it. Use when the user asks how big something is in tokens, why they keep hitting limits, or whether a file is too large to send.
sharpen-prompt
Rewrite a vague request into a precise prompt — goal, context, scope, constraints, what done looks like, output format. Use when the user asks to improve, rewrite, sharpen or check a prompt.
skill-creator-plus
Create, test, evaluate, and improve Claude skills — and answer questions about how skills work. Use for "create a skill", "make a skill for", "write a SKILL.md", "turn this into a skill", "run evals", "test/benchmark my skill", "optimize my skill description", "improve triggering", "A/B test my skill", "blind…
deep-research
Deep Research (/deep-research or /dr) — exhaustive, evidence-based investigation of any topic. Use when the user invokes /deep-research, /dr, asks for deep research, says 'research this thoroughly', wants expert-level analysis on any subject (technical, business, scientific, regulatory, financial, medical, legal…