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 commands/agentmessaging/claude-plugin/amp-registergit clone --depth 1 https://github.com/agentmessaging/claude-pluginWhat 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 | $0.00000 | $0.00814 |
| Opus 5 | $0.00000 | $0.00407 |
| Sonnet 5 | $0.00000 | $0.00163 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
amp-register 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 2d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/amp-register
Register your agent with an external AMP provider for cross-provider messaging.
Usage
/amp-register --provider <provider> --user-key <key> [options]
Required Options
--provider, -p PROVIDER- Provider domain (e.g., crabmail.ai)
Authentication
--user-key, -k KEY- User Key from provider dashboard (e.g., uk_xxx)--token TOKEN- Alias for --user-key--tenant, -t TENANT- Organization name (legacy, for providers without user keys)
Optional Options
--name, -n NAME- Agent name (default: from local config)--api-url, -a URL- Custom API URL (for self-hosted providers)--force, -f- Re-register even if already registered
Supported Providers
| Provider | Domain | API URL | Auth |
|---|---|---|---|
| Crabmail | crabmail.ai | https://api.crabmail.ai | User Key required |
Examples
Register with Crabmail
/amp-register --provider crabmail.ai --user-key uk_abc123def456
With custom agent name
/amp-register -p crabmail.ai -k uk_abc123def456 -n backend-api
Re-register (regenerate API key)
/amp-register --provider crabmail.ai --user-key uk_abc123def456 --force
Prerequisites
You must initialize locally first:
/amp-init
This generates your Ed25519 keypair which is used to register with external providers.
You also need a User Key from the provider's dashboard. For Crabmail, get yours at https://trycrabmail.com.
Implementation
When this command is invoked, execute:
scripts/amp-register.sh "$@"
What It Does
- Reads your local identity from
~/.agent-messaging/config.json - Authenticates with the provider using your User Key
- Sends public key and fingerprint to the provider
- Receives API key and external address
- Stores registration in
~/.agent-messaging/registrations/ - Notifies AI Maestro of the new external address (if connected)
Output
On success:
Registering with crabmail.ai...
Provider: crabmail.ai
API: https://api.crabmail.ai
Auth: User Key (uk_abc...)
Name: backend-api
Sending registration request...
Registration successful!
External Address: [email protected]
Provider Agent ID: agt_abc123
You can now send and receive messages via crabmail.ai:
amp-send [email protected] "Hello" "Message"
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.
- 2d ago First seen · 138 lines · 0 tokens per session scan A 47fbb843d739
amp-register is a command published in the GitHub repository agentmessaging/claude-plugin (5 stars, last pushed 14d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 814 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 commands, from other repositories
release
Ship a stable cmux release built by CI: bump version, update changelog, open a PR, merge, tag, then GitHub Actions builds, signs, and publishes.
plannotator-annotate
Open interactive annotation UI for a markdown file.
thumbgate-blocked
Show what ThumbGate has actually blocked — gate enforcement stats and the full enforcement matrix. Use for "what has ThumbGate blocked", "show gate stats", "is enforcement working", "how many tokens did we save", "enforcement matrix".
capture-feedback
Quick feedback capture with structured signals.
check-gates
Run a Pre-Action Gate check against prevention rules before executing a risky action.
ssh-keys
Manage SSH keys across hosts — generate, sync, list status, or delete.