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 skills/zach-source/claude-mailbox/mailboxnpx skills add zach-source/claude-mailbox --skill mailboxgit clone --depth 1 https://github.com/zach-source/claude-mailboxWrote 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/skills/zach-source/claude-mailbox/mailbox)<a href="https://agentmods.dev/skills/zach-source/claude-mailbox/mailbox"><img src="https://agentmods.dev/badge/skills/zach-source/claude-mailbox/mailbox.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 5.1 | $0.00112 | $0.00792 |
| Opus 5 | $0.00056 | $0.00396 |
| Sonnet 5 | $0.00022 | $0.00158 |
| Haiku 4.5 | $0.00011 | $0.00079 |
Grade A, and why
mailbox 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mailbox: cross-session coordination
Multiple Claude Code sessions run at once (different projects, branches, worktrees,
machines). The mailbox MCP lets them see each other and cross-talk. State is backed
by the shared beads_global database, so it works across projects and the fleet.
Push delivery (channels)
When the session is started as a channel (--dangerously-load-development-channels server:mailbox), peer messages arrive pushed as <channel source="mailbox" kind="dm|request|delegation|broadcast" from_sid="…" [request_id="…"]>…</channel>
events — you don't have to poll. React to them: for kind="request" answer with
respond_info passing the request_id; for kind="dm" reply with send_dm to the
from_sid; for kind="broadcast" just take it into account. Without the channel
flag, use poll_inbox / read_channel instead (same data, pull-based).
The one rule: a single leader on main
Exactly one session is the leader/orchestrator — the one on the main branch.
Everyone else is secondary. register_session auto-claims leadership when
you're on main; otherwise you're secondary and defer to the leader.
Protocol
- At session start — call
register_session(objective="<one line of intent>"). Thenlist_sessions()andget_leader()so you know who's around and who leads before touching shared state. - While working
update_objective(...)when your focus changes.set_status("blocked")when stuck,"idle"when waiting,"done"when finished.- Glance at
heartbeat()→inbox_count; if nonzero,poll_inbox().
- Before shared/destructive actions (editing
main,flake.lock, deploys, migrations): if you're secondary,broadcast("<intent>", channel="<project>")first, orrequest_info/send_dmthe relevant session. Don't stomp work in progress you can see inlist_sessions(). - Answer promptly — if
poll_inbox()shows a DM or the leader delegated work, respond. Another session may be waiting on you. - On exit —
set_status("done");deregister()(the server also does this automatically at process exit).
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 · 60 lines · 112 tokens per session scan A 8b00100ea0d7
mailbox is a skill published in the GitHub repository zach-source/claude-mailbox (1 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 792 once invoked, about $0.0006 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…