Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/lswith/imap-mcp/agents-mdgit clone --depth 1 https://github.com/lswith/imap-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/lswith/imap-mcp/agents-md)<a href="https://agentmods.dev/instructions/lswith/imap-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/lswith/imap-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.03255 | $0.03255 |
| Opus 5 | $0.01628 | $0.01628 |
| Sonnet 5 | $0.00651 | $0.00651 |
| Haiku 4.5 | $0.00326 | $0.00326 |
Grade A, and why
imap-mcp AGENTS.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 3d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
imap-mcp — rules for working in this repo
Generic IMAP → MCP server on Cloudflare Workers: one Worker, one package, at
the repository root. CLAUDE.md is a symlink to this file.
This file is the rules. The reasoning behind them lives in docs/architecture.md — read it before changing the sync path, the schema, or anything that reaches a model. Deploy mechanics are docs/deploy.md; the auth modes are docs/authentication.md; the contribution contract is CONTRIBUTING.md.
Layout
src/index.ts exports the Worker's three entry points: fetch (MCP server),
scheduled (sync enumeration), queue (fetch consumers).
src/imap/— the mailbox interface; the only placecf-imapis imported.src/sync/— everything that speaks IMAP. Write-policy refusals live here.src/mcp/— auth gate, tools, untrusted-content envelope, audit log.src/writes.ts— theWriteServicecontract between the two halves.src/log.ts— the only file insrc/that may callconsole.*.src/status.ts— theGET /statusdiagnostics document.migrations/— the D1 schema.
Tests: test/sync, test/mcp, test/imap/unit and test/repo run inside
workerd against the repo's own wrangler.jsonc; test/imap/protocol runs the
real cf-imap client against a scripted server under Node. A change to provider
behaviour must come with a protocol-harness test (see CONTRIBUTING.md).
Commands
pnpm install # single package, no workspace
pnpm run lint # biome check; lint:fix to write
pnpm run typecheck # wrangler types + tsc --noEmit
pnpm run test # vitest, both projects; test:watch, test:coverage
pnpm run dead-code # knip
pnpm run build # wrangler deploy --dry-run
pnpm run dev # wrangler dev (API-key mode locally)
pnpm run deploy # d1 migrations apply + wrangler deploy, in that order
pnpm run db:migrate:local / db:migrate:remote
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.
- 3d ago First seen · 229 lines · 3,255 tokens per session scan A 3aa864fe8222
imap-mcp AGENTS.md is an instructions file published in the GitHub repository lswith/imap-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 3,255 tokens to every session, about $0.0163 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
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.