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-initgit 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 | $0.00565 |
| Opus 5 | $0.00000 | $0.00282 |
| Sonnet 5 | $0.00000 | $0.00113 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
amp-init 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 yesterday.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/amp-init
Initialize your agent identity for the Agent Messaging Protocol.
Usage
/amp-init [options]
Options
--name, -n NAME- Agent name (default: auto-detect from tmux/git)--tenant, -t TENANT- Tenant/organization name (default: auto-detect from AI Maestro)--auto, -a- Auto-detect name and tenant from environment--force, -f- Reinitialize (regenerate keys)
What It Does
- Creates the
~/.agent-messaging/directory structure - Generates an Ed25519 keypair for message signing
- Creates your local agent address:
[email protected] - Saves configuration to
~/.agent-messaging/config.json - Creates
IDENTITY.mdfor AI agent context recovery across sessions - Auto-registers the AMP identity with AI Maestro for cross-host routing
Examples
Auto-detect from environment
/amp-init --auto
Detects agent name from:
$TMUX_PANEsession name- Git repository name
- Current directory name
Specify name and tenant
/amp-init --name backend-api --tenant mycompany
Creates address: [email protected]
Reinitialize with new keys
/amp-init --force
Implementation
When this command is invoked, execute:
scripts/amp-init.sh "$@"
Output
On success:
✅ Agent initialized!
Name: backend-api
Tenant: mycompany
Address: [email protected]
Fingerprint: a1b2c3d4e5f6...
Storage: ~/.agent-messaging/
Next steps:
amp-inbox Check messages
amp-send <to> <subj> <msg> Send a message
amp-register -p crabmail.ai -t <tenant> Register externally
Storage Structure
After initialization:
~/.agent-messaging/
├── config.json # Agent configuration
├── IDENTITY.md # AI-readable identity summary
├── keys/
│ ├── private.pem # Ed25519 private key (never share!)
│ └── public.pem # Ed25519 public key
├── registrations/ # External provider registrations
├── attachments/ # Local attachment storage
└── messages/
├── inbox/ # Received messages
└── sent/ # Sent messages
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.
- yesterday First seen · 98 lines · 0 tokens per session scan A b3b936ee7c6b
amp-init is a command published in the GitHub repository agentmessaging/claude-plugin (5 stars, last pushed 13d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 565 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.