Borrowing it
Nothing to install: this file belongs to michaellatman/mcp-get. 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/michaellatman/mcp-get/main/CLAUDE.mdgit clone --depth 1 https://github.com/michaellatman/mcp-getWrote 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/michaellatman/mcp-get/claude-md)<a href="https://agentmods.dev/instructions/michaellatman/mcp-get/claude-md"><img src="https://agentmods.dev/badge/instructions/michaellatman/mcp-get/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/michaellatman/mcp-get/claude-md"><img src="https://agentmods.dev/badge/instructions/michaellatman/mcp-get/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 | $0.00743 | $0.00743 |
| Opus 5 | $0.00371 | $0.00371 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
mcp-get 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md for mcp-get
Build/Lint/Test Commands
- Build:
npm run build - Test all:
npm test - Test single file:
npm run test:file src/__tests__/file.test.ts - Test with watch:
npm run test:watch - Test coverage:
npm run test:coverage - PR check:
npm run pr-check - Registry convert:
npm run registry:convert - Add package to registry:
npm run registry:add <package-file.json>
Code Style Guidelines
- Module System: ES Modules with
.jsextension in imports - Formatting: 2-space indentation, semicolons, single quotes
- Naming: camelCase for functions/variables, PascalCase for interfaces/classes, kebab-case for files
- Types: Explicit typing for functions, parameters, and returns; interfaces in dedicated files
- Error Handling: Use try/catch blocks with appropriate console.error messages and error propagation
- Testing: Jest with mocks for external dependencies; test files in
__tests__directories with.test.tsextension - Imports: Group by external packages first, then internal modules
- Async: Use async/await pattern for asynchronous code
- CLI Commands: Follow command pattern with consistent structure in
commands/directory - Configuration: Use
ConfigManagerfor managing persistent configurations
Testing Guidelines
- Use proper TypeScript interfaces for mocks (with mockReturnValueOnce, mockResolvedValueOnce, etc.)
- When testing CLI commands, mock all dependencies including inquirer, chalk, and utils
- Use
as unknown as MockTypepattern for properly typing Jest mocks - For interactive CLI testing, mock the inquirer.prompt response values
Package Registry Structure
- Packages are stored as individual JSON files in the
packages/directory - Each file follows the naming convention:
packageName.json(scoped packages usescope--name.json) - Package files contain metadata and environment variables
- To add a new package:
- Create a JSON file with the package metadata
- Use
npm run registry:add <package-file.json>to validate and add it to the registry - Always run
npm run pr-checkbefore submitting a PR to validate package structure
- Environment variables should be included in the package file under the
environmentVariableskey - The system will automatically find all packages by scanning the directory
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 · 58 lines · 743 tokens per session scan A 1d262f85b900
mcp-get CLAUDE.md is an instructions file published in the GitHub repository michaellatman/mcp-get (507 stars, last pushed 2mo ago), licensed MIT. It adds 743 tokens to every session, about $0.0037 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.