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 skills add lleontor705/agent-mailbox-mcp --skill docsgit clone --depth 1 https://github.com/lleontor705/agent-mailbox-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/skills/lleontor705/agent-mailbox-mcp/docs)<a href="https://agentmods.dev/skills/lleontor705/agent-mailbox-mcp/docs"><img src="https://agentmods.dev/badge/skills/lleontor705/agent-mailbox-mcp/docs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lleontor705/agent-mailbox-mcp/docs"><img src="https://agentmods.dev/badge/skills/lleontor705/agent-mailbox-mcp/docs.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00703 |
| Opus 5.5 | $0.00000 | $0.00281 |
| Sonnet 5.5 | $0.00000 | $0.00141 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
docs 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 1mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Mailbox MCP — Skill Guide for AI Agents
This document is designed for AI agents (Claude, GPT, Gemini, etc.) to understand how and when to use the agent-mailbox-mcp tools.
When to Use This Skill
Use the mailbox when you need to:
- Send information to another agent that isn't in your current conversation
- Delegate a task to a specialized agent and wait for results
- Coordinate work on shared resources (files, APIs, databases)
- Broadcast announcements to all agents in the system
- Track long-running work across multiple agents
Quick Decision Tree
Need to communicate with another agent?
├── Simple message → msg_send / msg_read_inbox / msg_acknowledge
├── Need a reply back → msg_request (waits for answer)
├── Tell everyone → msg_broadcast
├── Delegate complex work → a2a_submit_task / a2a_respond_task
├── Coordinate file access → resource_acquire / resource_release
└── Find other agents → msg_list_agents
Tool Patterns
Pattern 1: Fire and Forget
Send a message without waiting for a response.
msg_send(sender: "me", recipient: "logger", subject: "Event", body: "User completed onboarding")
Pattern 2: Request and Wait
Send a message and block until the reply arrives.
msg_request(sender: "me", recipient: "calculator", subject: "Compute", body: "What is 42 * 17?", timeout_seconds: 30)
→ { success: true, reply: { body: "714" } }
Pattern 3: Task Delegation (A2A)
For complex work that involves status tracking.
a2a_submit_task(from_agent: "me", to_agent: "researcher", message: "Find the latest pricing for AWS Lambda")
→ { task_id: "task-abc" }
# Later, check status
a2a_get_task(task_id: "task-abc")
→ { task: { status: "completed", artifacts: [...] } }
Pattern 4: Resource Lock
Before editing a shared file:
resource_acquire(resource_id: "shared/config.yaml", agent: "me", ttl_seconds: 60)
# ... do your work ...
resource_release(resource_id: "shared/config.yaml", agent: "me")
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 88 lines · 0 tokens per session scan A 97cd5a70cbf6
docs is a skill published in the GitHub repository lleontor705/agent-mailbox-mcp (1 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 703 tokens. 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
agent-teams
Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.
memory
Use this skill when Pioneer should proactively use durable memory or recalled context: decide whether memory can improve a turn, answer from remembered user/project facts, request memory tools, search/list/get stored memories, save durable preferences or project decisions, forget memories, audit or clean up memory, or…
subagents
Use this skill when Pioneer should delegate current-turn work to attached task-backed subagents, coordinate parallel child agents, wait for child results, review/revise/accept/cancel/detach attached work, or synthesize accepted child results into the parent answer.
runtime-diagnostics
Investigate Pioneer Gateway or desktop CPU, memory, slow work, queues, and runtime stalls using process metrics, local snapshots, bounded native profiles, and exact release symbols. Use for Pioneer performance diagnosis and interpreting its diagnostic artifacts.
agents-bridge
Skill "agents-bridge" from ellmos-ai/skills, covering agents-bridge — the lifeboat, auch: time capsule (deutsch), workflow & vorgehen and sicherheitsgrenzen.
tasks
Use this skill when Pioneer should create, inspect, update, reschedule, pause, resume, finish, cancel, troubleshoot, or configure delivery for durable tasks, scheduled tasks, recurring tasks, interval tasks, cron jobs, background work, or existing task state.