Borrowing it
Nothing to install: this file belongs to MarcinWalendowski/email-local-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/MarcinWalendowski/email-local-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/MarcinWalendowski/email-local-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/marcinwalendowski/email-local-mcp/claude-md)<a href="https://agentmods.dev/instructions/marcinwalendowski/email-local-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/marcinwalendowski/email-local-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/marcinwalendowski/email-local-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/marcinwalendowski/email-local-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 | $0.00951 | $0.00951 |
| Opus 5 | $0.00476 | $0.00476 |
| Sonnet 5 | $0.00190 | $0.00190 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
email-local-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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Email Local MCP
Guidance for Claude Code working in this repo. This is a public, released project (npm, GitHub Releases, a Homebrew tap, a published landing page), so the workspace-level "pre-launch, no backward-compatibility burden" exception in the
workspace root CLAUDE.md (~/loki-labs/CLAUDE.md)
does not apply here. Real people have this installed.
The marketing page is part of the product, not a separate thing
Every change that alters what the product does, or what is true about it, must update the landing page in the same session as the code. Not "later", not a follow-up task. If the page still describes the previous behaviour after your commit, the change is not finished.
The page source is site/index.html on main, and tools/publish-site
pushes it to the gh-pages branch. It used to live only on gh-pages, which
is the structural reason it drifted: nothing in the tree anyone edits ever
pointed at it, so no amount of good intentions kept it current. It is in main
now precisely so that a change to the code and a change to the page happen in
one working tree, in one diff, under one review.
What counts as "alters what is true about it":
- A new capability, auth mode, provider, tool, or platform.
- A change to how mail is handled, where credentials live, or what leaves the machine. These are load-bearing security claims, and the page states them as absolutes. An absolute claim is either true or it is a lie; there is no "mostly".
- Install instructions, supported OSes, prerequisites, pricing, licence.
- Anything the README's own security section says, because the page and the README must never disagree. When you edit one, diff the other.
What does not: internal refactors, test-only changes, comment edits, and anything a user could not observe.
Verify by grep, not by intention. After editing, grep the page for the claim
you invalidated and prove the old wording is gone — the same negative-control
rule tools/name-check exists to enforce for the old product name. A copy change
that "looks updated" is the exact failure mode this rule was written after.
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 · 87 lines · 951 tokens per session scan A 84a5aa241970
email-local-mcp CLAUDE.md is an instructions file published in the GitHub repository MarcinWalendowski/email-local-mcp (2 stars, last pushed 25d ago), licensed MIT. It adds 951 tokens to every session, about $0.0048 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.
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.