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/biff/poll-devgit clone --depth 1 https://github.com/punt-labs/biffWhat 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 | $0.00033 | $0.01439 |
| Opus 5 | $0.00016 | $0.00720 |
| Sonnet 5 | $0.00007 | $0.00288 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
poll-dev 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Input
Arguments: $ARGUMENTS
Task
biff is passive/pull. Incoming talk (invites + real-time messages) and /write
mail are held on the biff server and surface by MUTATING the descriptions of the
talk and read_messages tools. One command, three forms:
A. /biff-dev:poll-dev <duration> — start polling every <duration>
Trigger when $ARGUMENTS is a duration like 1m, 5m, 10m (parse the
{N}m/{N}s interval the way /loop does).
- Call
mcp__plugin_biff-dev_tty__set_poll_intervalwithintervalset to<duration>— this sets the server-side poll cadence. - Schedule the recurring model check with a
/loopjob at the same cadence:- Call
CronList; if any job'spromptfield exactly matches/biff-dev:poll-dev, callCronDeleteon it first (avoid duplicate loops). - Call
CronCreatewith:cron: the interval as a cron expression (1m→*/1 * * * *,2m→*/2 * * * *,5m→*/5 * * * *,10m→*/10 * * * *; sub-minute intervals use*/1 * * * *, the 1-minute cron floor).prompt:/biff-dev:poll-dev— the recurring job runs/biff-dev:poll-devwith NO argument (the no-arg check below). Do NOT put the duration in the loop body, or every fire would reschedule itself.recurring: truedurable: true
- Call
- Confirm what was set in one line: the poll interval, the loop job id from
CronCreate, and the 7-day durable-loop expiry. - Then fall through and run one check now (section C).
B. /biff-dev:poll-dev n — stop polling
Trigger when $ARGUMENTS is n, off, or stop. Turn the server-side cadence
off and remove the recurring model check.
- Call
mcp__plugin_biff-dev_tty__set_poll_intervalwithintervalset ton— this disables the server-side poll cadence. - Remove the recurring
/loopjob: callCronList; for any job whosepromptfield exactly matches/biff-dev:poll-dev, callCronDeleteon it. - Confirm in one line: polling disabled and the loop job removed. Do NOT fall through to a check.
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 · 97 lines · 33 tokens per session scan A bcb169e78937
poll-dev is a command published in the GitHub repository punt-labs/biff (2 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 1,439 once invoked, about $0.0002 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
meeting-listen
Play back a completed meeting summary as a voiced debate between personas.
meeting-hive
Run an autonomous PR/FAQ review meeting where four personas debate and reach consensus without user intervention.
vote
Assess whether a PR/FAQ should move forward with a structured go/no-go decision.
feedback
Incorporate feedback into PR/FAQ and redraft affected sections.
externalize
Generate an external press release from the PR/FAQ and CHANGELOG for a specific release.
import
Import an existing document and launch the full /prfaq workflow with extracted content.