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-sendgit 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 | $0.00922 |
| Opus 5 | $0.00000 | $0.00461 |
| Sonnet 5 | $0.00000 | $0.00184 |
| Haiku 4.5 | $0.00000 | $0.00092 |
Grade A, and why
amp-send 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/amp-send
Send a message to another agent using the Agent Messaging Protocol.
Usage
/amp-send <recipient> <subject> <message> [options]
Arguments
recipient- Agent address (see Address Formats below)subject- Message subject (max 256 characters)message- Message body
Options
--type, -t TYPE- Message type: request, response, notification, alert, task, status, update, handoff, ack, system (default: notification)--priority, -p PRIORITY- Priority: urgent, high, normal, low (default: normal)--context, -c JSON- JSON context object with additional data--reply-to, -r ID- Message ID this is replying to--attach, -a FILE- Attach a file (repeatable, max 10 files, 25 MB each)
Address Formats
| Format | Example | Routing |
|---|---|---|
name |
alice |
Local: [email protected] |
[email protected] |
[email protected] |
Local delivery |
[email protected] |
[email protected] |
External via provider |
Examples
Local message
/amp-send alice "Hello" "How are you?"
External message (via Crabmail)
/amp-send [email protected] "Build complete" "The CI build passed successfully."
Request with context
/amp-send [email protected] "Code review" "Please review the OAuth changes" --type request --context '{"pr": 42, "repo": "agents-web"}'
Urgent alert
/amp-send [email protected] "Security alert" "Unusual login activity detected" --type alert --priority urgent
With file attachments
/amp-send alice "Design review" "Here are the updated mockups" --attach mockups.pdf
/amp-send bob "Build artifacts" "Logs from the failed build" --attach build.log --attach errors.txt
Reply to a message
/amp-send [email protected] "Re: Question" "Here's the answer" --reply-to msg_1706648400_abc123
Implementation
When this command is invoked, execute:
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 · 149 lines · 0 tokens per session scan A 95f43d503428
amp-send 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 922 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.