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 manager-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/manager-setup)<a href="https://agentmods.dev/skills/kochetkov-ma/claude-brewcode/manager-setup"><img src="https://agentmods.dev/badge/skills/kochetkov-ma/claude-brewcode/manager-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/manager-setup"><img src="https://agentmods.dev/badge/skills/kochetkov-ma/claude-brewcode/manager-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 | $0.00017 | $0.00768 |
| Opus 5.5 | $0.00007 | $0.00307 |
| Sonnet 5.5 | $0.00003 | $0.00154 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
manager-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 15d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ambient manager prompt mode
This skill configures ambient prompt guidance only. It does not create, claim, or enforce a hard security wall.
Intent and scope
Resolve exactly one canonical mode -- status, install, upgrade, enable, disable, uninstall, purge -- plus the extras level and edit, then choose project state at .codex/brewtools/manager/state.json or personal prompt overrides under ~/.codex/manager/. Obtain confirmation before global writes. With no mode given, resolve status when state already exists and install otherwise. on, off, setup, remove, reset, create, update and cleanup are not modes: read them as the canonical verb, echo the canonical name back, and never print a retired alias as a command.
Modes
| Mode | Effect |
|---|---|
status |
Show hook registration, state source, level, override paths, and the no-security-wall limitation. Writes nothing, asks nothing. |
install |
Register the SessionStart and UserPromptSubmit handlers for this project and arm ambient prompt state. Idempotent: a second run leaves exactly one entry per event. |
upgrade |
Re-register the handlers from the current plugin version and restamp the version recorded in state, keeping the armed flag, the level and every override verbatim. It asks nothing, and it is the only thing that clears a stale version report. |
enable |
Arm ambient prompt state only. With nothing registered there is no handler to arm, so report not-installed and route the user to install. |
disable |
Disarm ambient prompt state only. Never touches registration: the handlers stay registered and no-op while disarmed. |
uninstall |
Deregister the handlers. State and prompt overrides are KEPT, so a later install returns to the same level and the same customized text. |
purge |
uninstall plus deletion of .codex/brewtools/manager/ and, in personal scope, the personal prompt override. The only destructive mode: state exactly what will be deleted before running it. |
level |
Set balanced or strict prompt wording. State only; it does not change sandbox or authorization. |
edit |
Update or remove prompt overrides after showing the diff. Changes injected text only, never registration or arm state. |
What ships with it
8 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.
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.
- 15d ago Changed · +4 lines ab08d8bdc7b7
- 1mo ago First seen · 38 lines · 17 tokens per session scan A 63bb11a50849
manager-setup is a skill published in the GitHub repository kochetkov-ma/claude-brewcode (32 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 768 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
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…
openclaw-setup
Set up, install, configure, and deploy OpenClaw (formerly ClawdBot/MoltBot) — a personal AI assistant that runs on your own devices and connects to messaging channels. Use when users ask to "set up OpenClaw," "install ClawdBot," "install MoltBot," "deploy a personal AI assistant," "configure OpenClaw on Mac," "deploy…
x402-payments
Build applications using the x402 protocol — Coinbase's open standard for HTTP-native stablecoin payments using the HTTP 402 status code. Use this skill when: Creating APIs that require USDC payments per request (seller/server side) Building clients or AI agents that pay for x402-protected resources (buyer/client…
cpp-reinforcement-learning
C++ Reinforcement Learning best practices using libtorch (PyTorch C++ frontend) and modern C++17/20. Use when: Implementing RL algorithms in C++ for performance-critical applications Building production RL systems with libtorch Creating replay buffers and experience storage Optimizing RL training with GPU acceleration…
prompt-optimizer
Optimize prompts for Claude's latest models (Claude 5 family — Opus 5, Sonnet 5, Fable 5 — plus the still-active Opus 4.8, Sonnet 4.6, and Haiku 4.5) using Anthropic's official prompt-engineering guidance. Use when users want to improve, refine, debug, or create prompts or system prompts for Claude. Triggers include…