poll

poll is a command for coding agents from punt-labs/biff. It costs 29 tokens per session (1,410 once invoked), scanned A, original, MIT.

A command that checks for incoming talk messages, invitations, and mail held on a biff server. It can check once or repeat at a chosen interval.

In plain words
What is it for?
Use it to start or stop periodic polling, or to check for messages immediately.
Why use it?
It removes the need to manually check for new messages. Repeating checks can surface incoming communication while you work.

Command

Part of the biff-dev plugin — 24 commands, 2 agents, 5 hooks shipped together

Install

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.

agentmods
npx agentmods add commands/punt-labs/biff/poll
Clone the repo
git clone --depth 1 https://github.com/punt-labs/biff

Or install biff-dev, the plugin that ships this one along with the rest of its 24 commands, 2 agents, 5 hooks.

Wrote 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.

agentmods badge for poll

README.md
[![agentmods](https://agentmods.dev/badge/commands/punt-labs/biff/poll.svg)](https://agentmods.dev/commands/punt-labs/biff/poll)
Your own site
<a href="https://agentmods.dev/commands/punt-labs/biff/poll"><img src="https://agentmods.dev/badge/commands/punt-labs/biff/poll.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,410 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.01410
Opus 5 $0.00015 $0.00705
Sonnet 5 $0.00006 $0.00282
Haiku 4.5 $0.00003 $0.00141

Measured 4d ago against content hash 6a49f4d40142, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

poll 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 4d 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.

plugin/commands/poll.md · 97 lines

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:poll <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).

  1. Call mcp__plugin_biff_tty__set_poll_interval with interval set to <duration> — this sets the server-side poll cadence.
  2. Schedule the recurring model check with a /loop job at the same cadence:
    • Call CronList; if any job's prompt field exactly matches /biff:poll, call CronDelete on it first (avoid duplicate loops).
    • Call CronCreate with:
      • 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:poll — the recurring job runs /biff:poll with NO argument (the no-arg check below). Do NOT put the duration in the loop body, or every fire would reschedule itself.
      • recurring: true
      • durable: true
  3. Confirm what was set in one line: the poll interval, the loop job id from CronCreate, and the 7-day durable-loop expiry.
  4. Then fall through and run one check now (section C).

B. /biff:poll n — stop polling

Trigger when $ARGUMENTS is n, off, or stop. Turn the server-side cadence off and remove the recurring model check.

  1. Call mcp__plugin_biff_tty__set_poll_interval with interval set to n — this disables the server-side poll cadence.
  2. Remove the recurring /loop job: call CronList; for any job whose prompt field exactly matches /biff:poll, call CronDelete on it.
  3. Confirm in one line: polling disabled and the loop job removed. Do NOT fall through to a check.

Read the full file on GitHub · 97 lines

Changes

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.

  1. 4d ago First seen · 97 lines · 29 tokens per session scan A 6a49f4d40142

Subscribe to this mod's changes

poll is a command published in the GitHub repository punt-labs/biff (2 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 1,410 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.