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/readgit 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 | $0.00006 | $0.00250 |
| Opus 5 | $0.00003 | $0.00125 |
| Sonnet 5 | $0.00001 | $0.00050 |
| Haiku 4.5 | $0.00001 | $0.00025 |
Grade A, and why
read 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.
This is a copy
89% identical to read-dev — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Call mcp__plugin_biff_tty__read_messages with no arguments. The tool retries a transport error once internally, per inbox, and never raises for a transport failure — every outcome below is a normal return value to check, never an error to catch.
If the result says "No new messages.", do not emit any text — this is a confirmed-empty result.
If the result starts with "Could not check ", surface it plainly and do not treat it as, or report it like, an empty inbox. This can appear standalone (every inbox failed) or as a leading line before rendered messages (some inboxes succeeded and are shown below it, one specific inbox could not be checked) — in the combined case, do not drop the warning line to make the output look clean; both facts are real.
Otherwise, emit the tool output exactly as returned — character for character, including the leading ▶ unicode character. Do not reformat, add commentary, wrap in code fences, convert to markdown tables, or add boxes around the output.
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 · 14 lines · 6 tokens per session scan A bffde33c45af
read is a command published in the GitHub repository punt-labs/biff (2 stars, last pushed 3d ago), licensed MIT. It adds 6 tokens to every session and 250 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to read-dev, differing in 4 lines, and is treated as a copy.
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.