What is brass-monkey CLAUDE.md?

Project instructions for preparing Brass-Monkey, a tool already used by some coding assistants, for installation in Claude. They define the project’s current goal, rules, and progress checklist.

Use them when adding Claude Code plugin and marketplace support, checking official formats, updating the packaging checklist, and preserving existing integrations.

They keep packaging work consistent across Claude, Gemini, and Antigravity and prevent implementation decisions from drifting away from the project plan.

brass-monkey CLAUDE.md — Instructions file for coding agents by actinon-com: Project instructions for preparing Brass-Monkey, a tool already

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 instructions/actinon-com/brass-monkey/claude-md

Clone the repo

git clone --depth 1 https://github.com/actinon-com/brass-monkey

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/actinon-com/brass-monkey/claude-md.svg)](https://agentmods.dev/instructions/actinon-com/brass-monkey/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/actinon-com/brass-monkey/claude-md"><img src="https://agentmods.dev/badge/instructions/actinon-com/brass-monkey/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,268 This file is loaded in full into every session.

When invoked 1,268 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.01268	$0.01268
Opus 5	$0.00634	$0.00634
Sonnet 5	$0.00254	$0.00254
Haiku 4.5	$0.00127	$0.00127

Measured 4d ago against content hash 41c65b46253e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brass-monkey CLAUDE.md 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 4d 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.

CLAUDE.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brass-Monkey — Claude Code Working Context

This file mirrors the intent of GEMINI.md for Claude Code. Where the two overlap, they must stay consistent. If you prefer a single source of truth, replace the "Shared Mandates" section below with an import of GEMINI.md (verify the current import syntax against the Claude Code docs before relying on it).

Current Initiative: Claude Packaging (v1.6.x → Claude-installable)

Brass-Monkey already ships as a working stdio MCP server consumed by Gemini CLI and Antigravity. The active goal is to make it installable and upgradeable on Claude (Claude Code plugin + marketplace as the primary path; a Claude Desktop bundle as a secondary path; raw claude mcp add as the universal fallback) while keeping Gemini/Antigravity working unchanged.

The work is tracked as a checklist in docs/claude-packaging-plan.md. Treat that file as the source of truth for progress: read it at the start of a session, check off items as their "Done when" criteria are met, and commit the updated file.

Non-negotiable rules for this initiative

Verify formats against live docs — do not trust memory. Before implementing the Claude Code plugin/marketplace phase or the Desktop bundle phase, fetch and read the current official documentation and follow the live schema:
- Claude Code docs map: https://docs.anthropic.com/en/docs/claude-code/claude_code_docs_map.md
- Claude docs: https://docs.claude.com Plugin manifest structure, marketplace manifest structure, and the desktop bundle format/name (.dxt vs .mcpb) all change; confirm them before writing any manifest.
Branch protection. main is protected. All work happens on a release-1.6.x (or release-1.7.0 if treated as a feature bump) branch. Never commit directly to main. Finalize via Pull Request; the Author (Matt) reviews and merges.
Additive, not forking. The stdio MCP server (src/mcp-server.ts → dist/bundle/index.js) is the shared core. Each ecosystem gets its own thin manifest pointing at the same launch command. Do not fork server logic per platform.
One phase per session. Use plan mode to propose before editing, gate each phase on npm test + a manual MCP Inspector check, commit, then compact/clear before the next phase.

Read the full file on GitHub · 99 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.

4d ago First seen · 99 lines · 1,268 tokens per session scan A 41c65b46253e

Subscribe to this mod's changes

brass-monkey CLAUDE.md is an instructions file published in the GitHub repository actinon-com/brass-monkey (2 stars, last pushed 11d ago), licensed MIT. It adds 1,268 tokens to every session, about $0.0063 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 2026-08-31.

ai ai-agent crm erp extension gemini-cli

orbiteus AGENTS.md

Instructions for orbiteus/orbiteus, covering agent / contributor policy, vendor-neutral copy and links, readme hero tagline (locked), stack and boring tech filter.

orbiteus/orbiteus · 642 tokens

S.HiveDesk AGENTS.md

AGENTS.md instructions for Akshit1018/S.HiveDesk, covering app builder workspace, 0. two worlds (read this first), project instructions, where you are and /workspace/startup.sh (required — you maintain this).

Akshit1018/S.HiveDesk · 9,260 tokens

able AGENTS.md

AGENTS.md instructions for codeyogi911/able, covering able, goal, working context, operating model and scope and autonomy.

codeyogi911/able · 768 tokens

gemini-watch GEMINI.md

Gemini CLI instructions for sudoax0n/gemini-watch, covering gemini watch extension, step 0 — setup preflight (runs every invocation), step 1 — parse input, step 2 — run the watch script and useful flags.

sudoax0n/gemini-watch · 766 tokens

able CLAUDE.md

Claude Code instructions for codeyogi911/able, a project described as: Agent-first, open-source ERP for service businesses. Able Desk — a support desk and CRM on Cloudflare Workers, operated through MCP — is the first application.

codeyogi911/able · 3 tokens

gemini-cli-desktop AGENTS.md

Instructions for Piebald-AI/gemini-cli-desktop, a project described as: Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.

Piebald-AI/gemini-cli-desktop · 6 tokens