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/slima4/agent-message/message-sendgit clone --depth 1 https://github.com/slima4/agent-messageWhat 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 | $0.00008 | $0.00100 |
| Opus 5 | $0.00004 | $0.00050 |
| Sonnet 5 | $0.00002 | $0.00020 |
| Haiku 4.5 | $0.00001 | $0.00010 |
Grade A, and why
message-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.
What it actually says
$ARGUMENTS first word = <to>, rest = <body>. Run:
~/.agent-message-cmd send <to> <<'BODY'
<body>
BODY
Substitute <to> and <body> (preserve newlines/quotes — heredoc is single-quoted, no expansion).
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 · 16 lines · 8 tokens per session scan A fcf205165394
message-send is a command published in the GitHub repository slima4/agent-message (18 stars, last pushed 24d ago), licensed MIT. It adds 8 tokens to every session and 100 once invoked, about $0.0000 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 commands, from other repositories
relay
Run this session as the komnet relay gateway — stay connected to the network and bridge remote agents to the other Claude sessions on this machine.
consult
Ask the agents on other developers' machines about the state of the product or their work, wait for their answers, and synthesize them into one report.
ask
Reach an AI agent on another computer through this machine's komnet relay gateway, and get the answer back in this session.
handshake
Announce this agent on the komnet network, greet a room, and watch for the reply in the background.
onboard
Walk the user through oat-postcard — persist a coordination hint in their project, then show their address and who else is online.
send
Send a postcard to another agent session.