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/sdk-e/mailbox/agents-mdgit clone --depth 1 https://github.com/SDK-E/mailboxWhat 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 | $0.00555 | $0.00555 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
mailbox 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 yesterday.
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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents working in this repo.
Stack
Single-package TypeScript ESM library + CLI bins. pnpm 11, Node >= 20 (CI runs 22). Vitest 4. No build framework — tsc to dist/.
Commands
pnpm verify— full gate: format:check, lint, typecheck, test:run, build. Must exit 0 with no warnings.pnpm dev— run the sink from source (tsx).- Individual:
pnpm run lint | format | typecheck | test:run | build.
Rules
- Run
pnpm verifybefore declaring any task done. - The HTTP API (
/api/health,/api/email,/api/email/:id,/api/email/all,/) and the message JSON shape are a stable wire protocol — consumers (app, auth, analytics repos) depend on exact shapes. Never break; extend only. - Zero runtime dependencies except
smtp-tester,@modelcontextprotocol/sdk,zod. Ask before adding anything else. - Keep files under ~200 lines. Exception:
src/ui.tsis one embedded HTML template string by design (ships inside the package without fs reads). - Bins must keep their shebang line as the first line;
tscpreserves it. - Tests bind ephemeral/free ports only — never hardcode 11025/11090 in tests.
- Conventional Commits (
feat:,fix:,chore:…). - No code comments unless required (e.g. eslint-disable rationale on its own line above).
Layout
src/server.ts—startMailbox()library entry: SMTP capture + HTTP API.src/ui.ts— embedded inbox UI.src/shared.ts— message types/formatting shared by server, CLI and MCP.src/client.ts— API client helpers used by CLI/MCP bins.src/env.ts— env resolution (MAIL_*), dotenv loading, production guard.src/bin/*— executable entries (mailbox,mailbox-cli,mailbox-mcp).test/raw-smtp.ts— dependency-free SMTP client used by tests.
Defaults worth remembering
- Ports: SMTP 11025, HTTP 11090 (env:
MAIL_SMTP_PORT,MAIL_HTTP_PORT; URL override:MAIL_HTTP_URL). - Loopback bind by default; refuses to start when
NODE_ENV=production. waitmatches only messages arriving after invocation.
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.
- yesterday First seen · 41 lines · 555 tokens per session scan A 7966bd5525b7
mailbox AGENTS.md is an instructions file published in the GitHub repository SDK-E/mailbox (0 stars, last pushed 9d ago), licensed MIT. It adds 555 tokens to every session, about $0.0028 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.