What is Mailbox AGENTS.md?

Repository instructions for Mailbox, a Node.js command-line application for email accounts, storage, and inbox workflows. They cover its package layout, commands, JSON output rules, and tests.

Use them when changing Mailbox's CLI, IMAP or SMTP code, storage, account migration, digest or monitoring workflows, build scripts, or contract tests.

They help an agent work within the existing package boundaries and preserve the command-line interface's JSON contract. They also make the correct build and test commands clear.

Mailbox AGENTS.md — Instructions file by leeguooooo

Install

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.

agentmods

npx agentmods add instructions/leeguooooo/mailbox/agents-md

Clone the repo

git clone --depth 1 https://github.com/leeguooooo/Mailbox

Made for: Codex, OpenCode.

Per session 492 This file is loaded in full into every session.

When invoked 492 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00492	$0.00492
Opus 5	$0.00246	$0.00246
Sonnet 5	$0.00098	$0.00098
Haiku 4.5	$0.00049	$0.00049

Measured 2d ago against content hash 866a51d63c5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

AGENTS.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

packages/ hosts the Node implementation:
- packages/cli/ CLI entry + command definitions
- packages/core/ IMAP/SMTP + storage + account migration
- packages/shared/ path resolution + JSON contract helpers
- packages/workflows/ digest/monitor/inbox workflows
mailbox-cli/ contains the npm launcher + platform binary packages.
scripts/ contains build helpers (notably scripts/build_binary.js).
docs/ holds CLI contract + release docs; legacy Python/MCP docs remain under docs/archive/.

Build, Test, and Development Commands

Install dependencies: pnpm install
Run tests: pnpm test
Build local pkg binary (and copy into mailbox-cli platform package): pnpm build:binary
Run dev CLI: pnpm -C packages/cli test or node packages/cli/bin/mailbox.js --help

Coding Style & Naming Conventions

Node.js (JavaScript). Keep modules small and side-effect-light.
Prefer explicit error objects in JSON output (success, error).
Avoid breaking JSON contract; add fields in a forward-compatible way.

Testing Guidelines

Contract tests live under packages/cli/test/ (vitest). Use MAILBOX_TEST_MODE=1 to avoid live IMAP/SMTP.
Prefer schema validation (docs/cli_json_schemas/*) to lock minimum stable JSON shapes.

Commit & Pull Request Guidelines

Follow the Conventional Commit style seen in history (feat:, fix:, refactor:); keep subjects ≤72 chars.
Include a brief body noting user-facing changes, risks, and docs updated.
PRs should describe context and testing performed (pnpm test, pnpm build:binary).
Link issues or TODOs and request reviewers for affected areas (operations, services, scripts).

Security & Configuration Tips

Never commit secrets; keep data/ contents (accounts, DBs, logs, attachments) local and gitignored.
Use environment variables or .env for provider credentials; prefer config templates in config_templates/ and examples in examples/.
When debugging, scrub email addresses and tokens from shared logs.

Read the full file on GitHub · 38 lines

Changes

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.

2d ago First seen · 38 lines · 492 tokens per session scan A 866a51d63c5b

Subscribe to this mod's changes

Mailbox AGENTS.md is an instructions file published in the GitHub repository leeguooooo/Mailbox (42 stars, last pushed 1mo ago), licensed MIT. It adds 492 tokens to every session, about $0.0025 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 2026-08-30.

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

Mailbox AGENTS.md