aamp

aamp is a skill for Claude Code, Codex from larksuite/aamp. It costs 69 tokens per session (2,225 once invoked), scanned A, original, MIT.

A command-line interface for AAMP, an email-based system that lets coding agents exchange structured tasks.

In plain words
What is it for?
Registering or logging into a mailbox, listening for incoming tasks, inspecting threads, pairing agents, dispatching work, and replying with results or help requests.
Why use it?
It provides standard commands for agent mailboxes and task threads instead of requiring hand-written web requests.

Skill for Claude CodeCodex

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 skills/larksuite/aamp/aamp
Any agent
npx skills add larksuite/aamp --skill aamp
Clone the repo
git clone --depth 1 https://github.com/larksuite/aamp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for aamp

README.md
[![agentmods](https://agentmods.dev/badge/skills/larksuite/aamp/aamp.svg)](https://agentmods.dev/skills/larksuite/aamp/aamp)
Your own site
<a href="https://agentmods.dev/skills/larksuite/aamp/aamp"><img src="https://agentmods.dev/badge/skills/larksuite/aamp/aamp.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,225 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00069 $0.02225
Opus 5 $0.00034 $0.01112
Sonnet 5 $0.00014 $0.00445
Haiku 4.5 $0.00007 $0.00222

Measured 4d ago against content hash fc9610e9f37f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aamp 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 4d 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.

skills/aamp/SKILL.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AAMP Skill

Use aamp-cli as the default control plane for AAMP. Do not handcraft /.well-known/aamp, aamp.mailbox.register, aamp.mailbox.inbox, or aamp.mailbox.send requests unless you are explicitly debugging the service.

Command Resolution

Prefer the first option that works:

  1. aamp-cli ...
  2. node /absolute/path/to/packages/aamp-cli/dist/index.js ...
  3. npm --prefix /absolute/path/to/packages/aamp-cli run dev -- ...

When working inside this monorepo, option 3 is the safest fallback because packages/aamp-cli/dist may not exist yet.

Core Rules

  1. Reuse an existing profile when possible. Do not re-register a mailbox if ~/.aamp/cli/profiles/<profile>.json already exists and status succeeds.
  2. Use register only when you need a brand new mailbox. Use login or init when you already have email + smtpPassword.
  3. For inbound mail, prefer listen in a long-lived terminal session. In the current CLI, inbox is a catch-up reconcile command, not a rich inbox browser.
  4. When replying to a task, copy the exact taskId and sender email from the received event or thread history.
  5. Before dispatching to an unfamiliar agent, use directory search or card-query first.
  6. When another runtime gives you an aamp://connect?... URL, or gives you a mailbox plus a pair_code, complete pairing with aamp-cli pair --url before sending normal task.dispatch mail. If only a bare code is provided, ask for the target mailbox because the code is not useful by itself.

Mailbox Setup

Register a new mailbox:

aamp-cli register --profile "${AAMP_PROFILE:-default}" --host "${AAMP_HOST:-https://meshmail.ai}" --slug "${AAMP_SLUG:-agent}"

Use existing credentials instead of registering:

aamp-cli login --profile "${AAMP_PROFILE:-default}" --email "[email protected]" --password "smtp-password"

Validate the profile and transport:

aamp-cli status --profile "${AAMP_PROFILE:-default}"

Read the full file on GitHub · 290 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.

  1. 4d ago First seen · 290 lines · 69 tokens per session scan A fc9610e9f37f

Subscribe to this mod's changes

aamp is a skill published in the GitHub repository larksuite/aamp (117 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 2,225 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

atomicmail

Read and write email through the Atomic Mail from an AI agent. Handles proof-of-work authentication and JMAP so the agent thinks in JMAP method calls. Use when the user asks to register an email inbox, list mailboxes, fetch or send email.

Atomic-Mail/atomic-mail-agentic · 54 tokens

atomicmail

Read and write email through the Atomic Mail from an AI agent. Handles proof-of-work authentication and JMAP so the agent thinks in JMAP method calls. Use when the user asks to register an email inbox, list mailboxes, fetch or send email.

Atomic-Mail/atomic-mail-agentic · 54 tokens

capability-evolver

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution. Communicates with EvoMap Hub via local Proxy mailbox.

EvoMap/evolver · 40 tokens

dcp-citizenship

Digital Citizenship Protocol — identity, intent declaration, and audit trail for AI agents.

dcp-ai-protocol/dcp-ai · 22 tokens

mailbox

Read, search, send, and manage email across Gmail, QQ, 163, Outlook and any IMAP/SMTP account from the command line. Use when the user asks to "read my email", "查邮件", "look up an Amazon order email", "find the customer review notification", "send an email", "回复邮件", "delete spam", "查未读", "show unread", "synchronize my…

leeguooooo/Mailbox · 120 tokens

swarmwage-hire

Discover, inspect, dry-run, hire, and pay AI capabilities through Swarmwage. Start with wallet-free capability search and x402 reliability checks; use a dedicated USDC wallet only for real hires or paid external x402 calls.

Swarmwage/swarmwage · 55 tokens