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/inboxgit clone --depth 1 https://github.com/punt-labs/beadleWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/punt-labs/beadle/inbox)<a href="https://agentmods.dev/commands/punt-labs/beadle/inbox"><img src="https://agentmods.dev/badge/commands/punt-labs/beadle/inbox.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00006 | $0.02216 |
| Opus 5 | $0.00003 | $0.01108 |
| Sonnet 5 | $0.00001 | $0.00443 |
| Haiku 4.5 | $0.00001 | $0.00222 |
Grade A, and why
inbox 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 5d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Input
Arguments: $ARGUMENTS
Task
Check beadle's email inbox. You are the beadle — this is your inbox, not the user's.
Argument routing
First, check if the argument matches a polling config command:
- Exactly one of
1m,5m,10m,15m,30m,1h,2h→ set polling interval - Exactly
n→ disable polling - Exactly
status→ show polling config
If none of the above match, treat the argument as a filter (existing behavior).
Polling interval (1m, 5m, 10m, 15m, 30m, 1h, 2h)
-
Call
set_poll_intervalwith the interval value. If it returns an error, report the error and stop — do not touch the cron job. -
Delete every existing
/inboxauto-poll cron job (see "Managing the cron job" below). This must happen before creating the new job, so two back-to-back/inbox 10mcalls leave exactly one cron job, not two. -
Create a new cron job:
CronCreate( cron: "*/10 * * * *", // from the table below, matching the requested interval recurring: true, durable: true, // persists across session restarts prompt: "/inbox" )Cron expressions:
1m→*/1 * * * *,5m→*/5 * * * *,10m→*/10 * * * *,15m→*/15 * * * *,30m→*/30 * * * *,1h→0 * * * *,2h→0 */2 * * *. All auto-poll jobs must setdurable: true— without it, the cron dies on session exit and the autonomous loop silently stops. -
Report a single confirmation line combining the
set_poll_intervalresponse and the new cron job ID. Example:polling set to 10m; cron job 12c9c370 created (durable, fires */10 * * * *).
Disable polling (n)
- Call
set_poll_intervalwithinterval: "n". If it returns an error, report the error and stop — do not touch the cron job. - Delete every existing
/inboxauto-poll cron job (see "Managing the cron job" below). - Confirm with the
set_poll_intervalresponse text.
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.
- 5d ago First seen · 179 lines · 6 tokens per session scan A 628e84d6728d
inbox is a command published in the GitHub repository punt-labs/beadle (3 stars, last pushed 2d ago), licensed MIT. It adds 6 tokens to every session and 2,216 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 2026-08-31.
Other commands, from other repositories
statusline
Show the governor fleet in your Claude Code statusline. Explicit, opt-in, and chains — it never replaces an existing statusline.
vox
Enable or disable vox in this repo.
talk-dev
Start a real-time conversation with a teammate or agent.
talk
Start a real-time conversation with a teammate or agent.
scout-setup
First-time install of Scout. Detects connected tools, collects user details, and hands off to scoutctl bootstrap install. For upgrading an existing vault, run /scout-update.
write-dev
Send a message to a teammate.