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/vitalio-sh/thunderbird-cli/agents-mdgit clone --depth 1 https://github.com/vitalio-sh/thunderbird-cliWrote 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/vitalio-sh/thunderbird-cli/agents-md)<a href="https://agentmods.dev/instructions/vitalio-sh/thunderbird-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/vitalio-sh/thunderbird-cli/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 | $0.01759 | $0.01759 |
| Opus 5 | $0.00879 | $0.00879 |
| Sonnet 5 | $0.00352 | $0.00352 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade A, and why
thunderbird-cli 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 5d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — thunderbird-cli
Repo guide for AI coding agents working in this codebase (Cursor, Cline, Codex CLI, Claude Code, Windsurf, Aider, etc.).
Looking for the end-user skill that teaches Claude how to use this tool? That's in
skills/thunderbird-cli/. This file is about working on the code.
What this repo ships
Four published artifacts, one architecture:
| Artifact | What | Where |
|---|---|---|
thunderbird-cli |
tb CLI (38 commands) |
cli/ → npm: thunderbird-cli |
thunderbird-cli-bridge |
Stateless HTTP↔WS proxy daemon | bridge/ → npm: thunderbird-cli-bridge |
thunderbird-cli-mcp |
MCP server (12 tools for Claude Desktop) | mcp/ → npm: thunderbird-cli-mcp |
| Thunderbird WebExtension | WS client inside Thunderbird | extension/ → signed XPI on addons.thunderbird.net |
AI Agent ─→ tb CLI ─┐
├─→ bridge daemon ─→ Thunderbird WebExtension ─→ messenger.* APIs → your accounts
Claude ─→ tb-mcp MCP ─┘ HTTP :7700 WebSocket :7701
Everything localhost-only. Thunderbird holds credentials; no creds pass through the agent.
Setup (before editing)
npm install # installs workspace deps for cli/, bridge/, mcp/
npm test # 46 CLI/bridge integration tests
npm run test:mcp # 34 MCP server tests
npm run bridge # start bridge (needed for live tests; not for unit tests)
Node 20+ required. All three packages are ES modules ("type": "module").
Conventions you need to follow
Code style
- ES modules throughout,
"type": "module"in everypackage.json. - CLI framework:
commander.js. Command definitions incli/src/cli.js; HTTP client + formatters incli/src/client.js. - Bridge: vanilla Node
http+ws. Zero business logic — it's a UUID-correlated proxy. Don't add state. - MCP server:
@modelcontextprotocol/sdk. Stdio transport. Reusescli/src/client.js— don't re-implement the HTTP client inmcp/. - Extension: pure WebExtension (
manifest_version: 2). No Experiment APIs. Compatible with Thunderbird 128+.
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.
- 5d ago First seen · 150 lines · 1,759 tokens per session scan A ab950a8e754d
thunderbird-cli AGENTS.md is an instructions file published in the GitHub repository vitalio-sh/thunderbird-cli (40 stars, last pushed 1mo ago), licensed MIT. It adds 1,759 tokens to every session, about $0.0088 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.
Other instructions, from other repositories
imap-mcp-pro CLAUDE.md
Claude Code instructions for Temple-of-Epiphany/imap-mcp-pro, covering claude.md, project overview, common development commands, architecture and core components.
mcp-email-server AGENTS.md
AGENTS.md instructions for Wh1isper/mcp-email-server, covering repository overview, project conventions, current architecture direction, development workflow and documentation requirements.
imap-mcp-server AGENTS.md
AGENTS.md instructions for nikolausm/imap-mcp-server, covering agents.md, architecture, build / test commands, security rules (must follow) and conventions.
better-email-mcp CLAUDE.md
Claude Code instructions for n24q02m/better-email-mcp, covering claude.md - better-email-mcp, commands, setup, lint & type check and fix.
imap-mcp-server CLAUDE.md
Claude Code instructions for nikolausm/imap-mcp-server, covering claude.md and claude-specific notes.
agenticmail CLAUDE.md
Claude Code instructions for agenticmail/agenticmail, covering claude code instructions for agenticmail, option a — one-line installer (recommended) and option b — manual.