Borrowing it
Nothing to install: this file belongs to w21180239/mcp-outlook-lite. 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/w21180239/mcp-outlook-lite/main/CLAUDE.mdgit clone --depth 1 https://github.com/w21180239/mcp-outlook-liteWrote 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/w21180239/mcp-outlook-lite/claude-md)<a href="https://agentmods.dev/instructions/w21180239/mcp-outlook-lite/claude-md"><img src="https://agentmods.dev/badge/instructions/w21180239/mcp-outlook-lite/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/w21180239/mcp-outlook-lite/claude-md"><img src="https://agentmods.dev/badge/instructions/w21180239/mcp-outlook-lite/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 | $0.00398 | $0.00398 |
| Opus 5 | $0.00199 | $0.00199 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
mcp-outlook-lite 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.
What it actually says
mcp-outlook-lite — Agent Instructions
The lightest Outlook MCP server — zero secrets, PKCE auth, 46 tools via Microsoft Graph API.
Architecture
- TypeScript, compiled to ES2022 ESM (
npm run build→dist/) - Tests: vitest (
npm test) — 769 tests, ~81% coverage - Entry:
server/index.ts→ dispatcher → tool handlers - Auth: OAuth 2.0 PKCE + device code flow in
server/auth/ - All logging goes to stderr (stdout reserved for MCP protocol)
Key conventions
- Tool handlers return MCP responses (never throw) — use
createToolError()/convertErrorToToolError() - Debug output: use
debug()fromserver/utils/logger.js(gated byDEBUGenv) - Warnings: use
warn()fromserver/utils/logger.js(always outputs) - Never use
console.login production code (corrupts MCP stdio transport) - All Graph API calls scoped to
/me/(authenticated user only) - Shared types in
server/types.ts— useMCPResponse,ToolHandler, etc.
Testing
npm test # 769 tests
npm run test:watch # watch mode
npm run typecheck # type checking
npm run build # compile to dist/
Test files live in server/tests/, mirroring the source structure. Use server/tests/helpers/mockAuthManager.js for mocking auth in tool tests.
Adding a new tool
- Create handler in
server/tools/<category>/newTool.ts - Add schema in
server/schemas/<category>Schemas.ts - Export from
server/tools/index.ts - Register in
server/tools/dispatcher.ts - Write tests in
server/tests/tools/<category>/
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 · 40 lines · 398 tokens per session scan A 332ce1e90e5c
mcp-outlook-lite CLAUDE.md is an instructions file published in the GitHub repository w21180239/mcp-outlook-lite (0 stars, last pushed 5mo ago), licensed MIT. It adds 398 tokens to every session, about $0.0020 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.