Borrowing it
Nothing to install: this file belongs to fledgeling-co/sift-apple-mail-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/fledgeling-co/sift-apple-mail-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/fledgeling-co/sift-apple-mail-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/fledgeling-co/sift-apple-mail-mcp/claude-md)<a href="https://agentmods.dev/instructions/fledgeling-co/sift-apple-mail-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/fledgeling-co/sift-apple-mail-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/fledgeling-co/sift-apple-mail-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/fledgeling-co/sift-apple-mail-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 | $0.05901 | $0.05901 |
| Opus 5 | $0.02950 | $0.02950 |
| Sonnet 5 | $0.01180 | $0.01180 |
| Haiku 4.5 | $0.00590 | $0.00590 |
Grade C, and why
sift-apple-mail-mcp CLAUDE.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
npm run build # rm -rf dist && tsgo -p tsconfig.build.json How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Operating rules, load before writing code
Two operating specs govern all code in this repo. Read them before generating code and apply them as you write, because they're the rules the code-review skill blocks on:
docs/CODING_PRACTICES.md(cited as CP §n), TypeScript boundary safety, security, and cross-cutting logic-bug patterns. Before reporting any change done, run the CP §7 agent self-review over your diff and say which files you covered.docs/NEW_PROJECT_BEST_PRACTICES.md(cited as BP §n), stack defaults and day-one decisions. Most of it doesn't apply here; see "Divergences" below before taking one of its defaults.
CP overrides for this repo, which CP §3's own precedence rule licenses (CLAUDE.md wins over CP). Naming them by section, both directions:
- Doesn't apply here: CP §2 (NestJS), CP §3 (Next.js and React 19), CP §6.1 to §6.9 (auth boundaries, cookies, Mongoose, uploads, HTML email, CSP, operational guardrails for a web app), §6.11 to §6.13 (Redis, Vercel cron, React Query), §6.15 (client React and React Native). There's no HTTP surface, no browser, no users to authenticate.
- Still binds, in full: CP §1 (TypeScript boundary safety), CP §4's injection rules (parameterise every SQL query), dependency hygiene, logging and secret-handling rules, CP §5 (style, diff scope, don't weaken tests), and CP §6.14 (logic-bug patterns). CP §6.10 (cross-service contracts) now binds: the daemon and the proxy talk over a Unix socket, so a changed wire field has to move on both sides in one change.
- CP §7's verification line reads
npm run gatehere. It says to runtsc --noEmitand the lint gate; this repo's typecheck istsgo --noEmitand its lint gate isoxlintplus a control-character check (see Divergences).
Behaviour under ambiguity:
- Think before acting. State assumptions explicitly. If there are two readings, present both; don't pick silently.
- Simplicity first. Minimum change that solves the problem. No speculative abstractions.
- Surgical changes. Don't improve adjacent code. Every changed line traces to the request.
- Goal-driven execution. Turn the task into verifiable success criteria first, then loop until they're met.
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 · 164 lines · 5,901 tokens per session scan C ee9391b9f08f
sift-apple-mail-mcp CLAUDE.md is an instructions file published in the GitHub repository fledgeling-co/sift-apple-mail-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 5,901 tokens to every session, about $0.0295 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.