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/larksuite/aamp/aampnpx skills add larksuite/aamp --skill aampgit clone --depth 1 https://github.com/larksuite/aampWrote 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/larksuite/aamp/aamp)<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>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 | $0.00069 | $0.02225 |
| Opus 5 | $0.00034 | $0.01112 |
| Sonnet 5 | $0.00014 | $0.00445 |
| Haiku 4.5 | $0.00007 | $0.00222 |
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.
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:
aamp-cli ...node /absolute/path/to/packages/aamp-cli/dist/index.js ...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
- Reuse an existing profile when possible. Do not re-register a mailbox if
~/.aamp/cli/profiles/<profile>.jsonalready exists andstatussucceeds. - Use
registeronly when you need a brand new mailbox. Useloginorinitwhen you already haveemail + smtpPassword. - For inbound mail, prefer
listenin a long-lived terminal session. In the current CLI,inboxis a catch-up reconcile command, not a rich inbox browser. - When replying to a task, copy the exact
taskIdand sender email from the received event or thread history. - Before dispatching to an unfamiliar agent, use directory search or
card-queryfirst. - When another runtime gives you an
aamp://connect?...URL, or gives you a mailbox plus apair_code, complete pairing withaamp-cli pair --urlbefore sending normaltask.dispatchmail. 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}"
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.
- 4d ago First seen · 290 lines · 69 tokens per session scan A fc9610e9f37f
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.
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.
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.
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.
dcp-citizenship
Digital Citizenship Protocol — identity, intent declaration, and audit trail for AI agents.
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…
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.