Borrowing it
Nothing to install: this file belongs to AutomoxCommunity/automox-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AutomoxCommunity/automox-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/AutomoxCommunity/automox-mcpWrote 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/instructions/automoxcommunity/automox-mcp/claude-md)<a href="https://agentmods.dev/instructions/automoxcommunity/automox-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/automoxcommunity/automox-mcp/claude-md/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/instructions/automoxcommunity/automox-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/automoxcommunity/automox-mcp/claude-md.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 | $0.02772 | $0.02772 |
| Opus 5 | $0.01386 | $0.01386 |
| Sonnet 5 | $0.00554 | $0.00554 |
| Haiku 4.5 | $0.00277 | $0.00277 |
Grade A, and why
automox-mcp 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 9d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
automox-mcp — project instructions
Repo-specific invariants for this MCP server. These are self-enforcing reminders: follow them without waiting to be asked. (General working preferences live in the user-global ~/.claude/CLAUDE.md.)
Adding / removing / renaming a tool
A tool's name and count appear in several hand-maintained places. When you change the tool set, update all of these in the same change — CI guards some, but not all:
| Location | What to update | CI-guarded? |
|---|---|---|
src/automox_mcp/tools/<domain>_tools.py |
the @server.tool registration |
— |
src/automox_mcp/tools/meta_tools.py _DOMAIN_CATALOG |
the (name, description) entry (the model-facing discovery directory) |
✅ test_doc_tool_counts.py |
docs/tool-reference.md |
the bullet and its ## Domain (N tools) section count and the top "all N tools" header |
✅ test_doc_tool_counts.py |
README.md + mcpb/manifest.json |
total / read / write counts | ✅ test_doc_tool_counts.py |
mcpb/manifest.json tools[] (+ prompts[] on prompt changes) |
regenerate, don't hand-edit: uv run python scripts/generate_mcpb_catalog.py (feeds Claude Desktop's "Tools"/"Prompts" details sections) |
✅ test_doc_tool_counts.py |
docs/api-coverage.md |
coverage map / omission rationale / build-backlog rows | ❌ manual — easy to forget |
tests/smoke_production.py |
live read-side coverage for new read tools (not destructive writes) | ❌ manual, not in CI |
CHANGELOG.md |
the entry under the active version | ❌ manual |
The current split is 133 tools / 85 read / 48 write. discover_capabilities is intentionally excluded from _DOMAIN_CATALOG.
Adding / removing an MCP resource or MCP App
Resources (incl. ui:// MCP App UIs) and the Apps extension have their own hand-maintained surfaces — and unlike tools, none of them are CI-guarded:
| Location | What to update | CI-guarded? |
|---|---|---|
src/automox_mcp/resources/<name>_resources.py + resources/__init__.py |
the @server.resource registration + its register_* call |
— |
docs/tool-reference.md + mcpb/manifest.json |
the "N MCP resources" count | ✅ test_doc_tool_counts.py |
docs/tool-reference.md ## MCP Resources |
the resource-table row and (for Apps) the ### MCP Apps note |
❌ manual — easy to forget |
CHANGELOG.md |
the entry under the active version | ❌ manual |
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.
- 9d ago First seen · 90 lines · 2,772 tokens per session scan A a3c2c320d1cf
automox-mcp CLAUDE.md is an instructions file published in the GitHub repository AutomoxCommunity/automox-mcp (12 stars, last pushed 6d ago), licensed MIT. It adds 2,772 tokens to every session, about $0.0139 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.