Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add punt-labs/prfaq/plugin install prfaq-devWrote 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/prfaq/meeting-listen)<a href="https://agentmods.dev/commands/punt-labs/prfaq/meeting-listen"><img src="https://agentmods.dev/badge/commands/punt-labs/prfaq/meeting-listen/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/punt-labs/prfaq/meeting-listen"><img src="https://agentmods.dev/badge/commands/punt-labs/prfaq/meeting-listen.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00012 | $0.05175 |
| Opus 5 | $0.00006 | $0.02587 |
| Sonnet 5 | $0.00002 | $0.01035 |
| Haiku 4.5 | $0.00001 | $0.00517 |
Grade A, and why
meeting-listen 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 10d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR/FAQ Meeting Listen
Play back a completed meeting summary as a voiced conversation between four personas — Wei, Priya, Alex, and Dana — each speaking in their own voice. This is post-production: the meeting already happened, you're listening to the recording.
Prerequisites
Check whether mcp__plugin_vox_mic__unmute is available. Set a session flag:
- Voiced mode — TTS is available. Voices will be used.
- Text-only mode — TTS is not available. Tell the user: "TTS plugin not available — playing back as text-only transcript. Install punt-vox for voiced playback." Continue with all steps below, but skip all
mcp__plugin_vox_mic__*calls. Print dialogue as attributed text instead.
Load ${CLAUDE_PLUGIN_ROOT}/skills/prfaq/references/plain-style.md — generative prose rules (no em dash, no negative parallelism, no corporate-register vocabulary, no value-claim filler, no explaining the document to the reader). The persisted meeting summary you read in step 2 already passed through prose_lint.py when it was written, but every line of dialogue you construct in step 6b, and every narrator or recap segment you author in step 7, is new text that is spoken or printed and never written to a file — apply every rule in plain-style.md to that new text before it is voiced or printed.
Steps
-
Find the meeting summary. If
$ARGUMENTSspecifies a path, use it. Otherwise, use Glob to find meeting summaries with both patterns:meetings/meeting-summary-*.md(interactive meetings)meetings/meeting-hive-summary-*.md(hive meetings)
Search from the user's current working directory (not the plugin root). If no results, broaden the search using
**/meetings/meeting-summary-*.mdand**/meetings/meeting-hive-summary-*.mdto find meetings in subdirectories.If multiple exist, parse the
YYYY-MM-DDdate from each filename and choose the latest date. If there are multiple on the same date, choose the one with the highest numeric suffix (e.g.,...-2.mdafter the unsuffixed original). If none exist, tell the user: "No meeting summaries found. Run/prfaq:meetingor/prfaq:meeting-hivefirst."
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.
- 10d ago First seen · 227 lines · 12 tokens per session scan A bdc2db3f7531
meeting-listen is a command published in the GitHub repository punt-labs/prfaq (25 stars, last pushed 8d ago), licensed MIT. It adds 12 tokens to every session and 5,175 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 2026-08-30.
Other commands, from other repositories
oracle-dev
Generate property-based test harness using Lean 4 model as oracle.
refine-dev
Verify code refines Z specification via abstraction function and commutativity checks.
refine
Verify code refines Z specification via abstraction function and commutativity checks.
setup-dev
Install and configure fuzz, probcli, and lean dependencies.
setup
Install and configure fuzz, probcli, and lean dependencies.
contracts-dev
Generate runtime contracts (preconditions, postconditions, invariants) from a Z specification.