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/punt-labs/beadle/sendgit clone --depth 1 https://github.com/punt-labs/beadleWhat 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 | $0.00012 | $0.00375 |
| Opus 5 | $0.00006 | $0.00187 |
| Sonnet 5 | $0.00002 | $0.00075 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
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
Input
Arguments: $ARGUMENTS
Task
Send something to the user or a specified recipient via the best available channel. Today, email is the only channel. In the future, this command will support Signal and other channels.
Parse the arguments
The arguments describe what to send and optionally the channel. Examples:
/send me an email summary— send via email (explicit)/send me a summary— send via email (default, only channel today)/send this to [email protected]— send to a specific recipient via email
Default behavior
- Default recipient: the owner (ask if unclear)
- Default channel: email (the only channel currently available)
Compose and send
- Compose the content based on the arguments. Use plain text.
- Choose a clear, descriptive subject line.
- Call
send_emailwith the recipient, subject, and body.
The result is already formatted by a PostToolUse hook and displayed in the panel. Do not repeat or reformat the send confirmation.
Future channels
When new channels are added (Signal, etc.), this command will route based on the via argument or infer the channel from context. For now, all sends go through email.
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 · 40 lines · 12 tokens per session scan A d46a16d589ce
send is a command published in the GitHub repository punt-labs/beadle (3 stars, last pushed 2d ago), licensed MIT. It adds 12 tokens to every session and 375 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
logs
Analyze server logs to diagnose errors, exceptions, and unexpected behavior.
browser
Debug and fix browser issues by inspecting, diagnosing, and resolving visual or technical problems.
types
Debug and fix TypeScript type errors with systematic analysis and expert guidance.
check-dev
Type-check a Z specification with fuzz.
swarm-planner
Generates a structured execution plan with dependency tracking using the Swarms-inspired planning methodology.
review-queue
Display and manage the human review queue for parallel autonomous operations.