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 allemaar/open-skills --skill agent-mailboxgit clone --depth 1 https://github.com/allemaar/open-skillsWrote 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/allemaar/open-skills/agent-mailbox)<a href="https://agentmods.dev/skills/allemaar/open-skills/agent-mailbox"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/agent-mailbox/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/allemaar/open-skills/agent-mailbox"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/agent-mailbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.17593 |
| Opus 5 | $0.00016 | $0.08797 |
| Sonnet 5 | $0.00007 | $0.03519 |
| Haiku 4.5 | $0.00003 | $0.01759 |
Grade A, and why
agent-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 11d 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 — 638 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/agent-mailbox
Coordinate two or more agents by exchanging append-only Markdown messages in a Handler-visible shared folder. The transport may be local filesystem, Git, a free registered Lyt (Link Your Think™) vault, or a sync-share such as OneDrive or SMB. The mailbox messages form an auditable causal graph rather than a chat transcript hidden in one runtime.
This is an agent operating protocol. It is not a broker, queue, daemon, authentication boundary, or a message-transport service. For registered cross-machine delivery, use a dedicated transport product and point this skill at the folder it exposes. Use this skill to teach agents how to handshake, divide work, deliver artifacts, listen, react once, recover, resume, and close over the mailbox the Handler supplies.
Structured execution spec: protocol.yon. Read it for the canonical rules and step sequence; this file is explanation. The two must stay in sync — if you edit one, update the other and refresh the @STAMP date.
First exchange: references/QUICKSTART.md. Templates: references/MESSAGE-TEMPLATE.md and references/PRIMER-TEMPLATE.md. Active collaboration resources: resources/INDEX.md. Operating choices: references/OPERATING-MODES.md. Transport and runtime diagnosis: references/CONNECTION-GUIDES.md. Field guidance: references/FIELD-GUIDE.md. Public evidence and known gaps: references/VALIDATION.md.
Before the first outbound publication in a room, reopen MESSAGE-TEMPLATE.md and copy its complete canonical envelope. Do not recreate meta.mailbox from memory. Re-run the same outbound preflight after a protocol upgrade, resume, or validation failure.
Fast routing
| Situation | Load now |
|---|---|
| First simple exchange | Quickstart, message template, base handshake and disposition rules |
| Existing room | Fast activation below, primer, complete inbox reconciliation |
| Three or more agents or competing claims | FULL profile rules |
| Continued collaboration | The one runtime default below and its exact lazy YON package |
| Miss, stale readiness, or cursor contradiction | missed-message-recovery.yon before re-arm |
| Divide work, consult, verify, hand off, repair, or learn | resources/INDEX.md, then only the operation needed |
What ships with it
24 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.
- protocol.yon 77 KB
- protocols/collab-window.yon 13 KB
- protocols/missed-message-recovery.yon 12 KB
- protocols/scheduled-collab.yon 16 KB
- references/CONNECTION-GUIDES.md 26 KB
- references/FIELD-GUIDE.md 15 KB
- references/MESSAGE-TEMPLATE.md 13 KB
- references/OPERATING-MODES.md 8.2 KB
- references/PRIMER-TEMPLATE.md 12 KB
- references/QUICKSTART.md 8.3 KB
- references/VALIDATION.md 27 KB
- resources/ACTIVATION-PRIMER.md 917 B
- resources/COMPOSITION.md 1.3 KB
- resources/CTA-SIGNAL-EXTRACTION.md 2.2 KB
- resources/experimental/INDEX.md 985 B
- resources/experimental/PATTERN-BANK.md 4.5 KB
- resources/INDEX.md 2.5 KB
- resources/PATTERNS.md 6.1 KB
- resources/recipes/FAN-OUT-FAN-IN.md 1.3 KB
- resources/recipes/HANDOFF.md 1.3 KB
- resources/recipes/POSTMORTEM.md 1.4 KB
- resources/recipes/REVIEW.md 1.1 KB
- resources/recipes/SELF-HEALING.md 2.6 KB
- resources/WORKING-AGREEMENT.md 1.6 KB
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.
- 11d ago First seen · 638 lines · 33 tokens per session scan A dfa1366564a4
agent-mailbox is a skill published in the GitHub repository allemaar/open-skills (14 stars, last pushed 24d ago), licensed Apache-2.0. It adds 33 tokens to every session and 17,593 once invoked, about $0.0002 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 skills, from other repositories
polis-protocol
Set up and run a self-improving, multi-vendor AI agent team with the Polis Protocol — a markdown polis/ folder where each agent is a citizen with a capability card, tasks are contracts routed to whoever has the best track record by a learning router, settled work files lessons that compound into team memory, and…
media
Skill "media" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
_data
Skill "_data" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.