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.
git clone --depth 1 https://github.com/punt-labs/biffWrote 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/biff/write-dev)<a href="https://agentmods.dev/commands/punt-labs/biff/write-dev"><img src="https://agentmods.dev/badge/commands/punt-labs/biff/write-dev/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/biff/write-dev"><img src="https://agentmods.dev/badge/commands/punt-labs/biff/write-dev.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 | $0.00006 | $0.00307 |
| Opus 5.5 | $0.00002 | $0.00123 |
| Sonnet 5.5 | $0.00001 | $0.00061 |
| Haiku 4.5 | $0.00001 | $0.00031 |
Grade A, and why
write-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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- write — 88% identical, 10 lines differ
What it actually says
Input
Arguments: $ARGUMENTS
Parse as: first token is the recipient username (strip leading @ if present), remaining tokens are the message body.
Example: kai hey, ready for code review? → to="kai", message="hey, ready for code review?"
Task
Call mcp__plugin_biff-dev_tty__write with to and message set to the parsed values. The result is already formatted by a PostToolUse hook and displayed above. Do not repeat or reformat the data.
Auto-poll for response
After sending the message, ensure a polling loop exists to catch replies:
- Call
CronListand check if any listed job has apromptfield that exactly matches/biff-dev:read-dev. - If no existing
/biff-dev:read-devcron, callCronCreatewith:cron:*/5 * * * *prompt:/biff-dev:read-devrecurring: truedurable: true
- Do not mention the cron setup or send any other text to the user.
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.
- 1mo ago First seen · 31 lines · 6 tokens per session scan A b76daed43195
write-dev is a command published in the GitHub repository punt-labs/biff (2 stars, last pushed today), licensed MIT. It adds 6 tokens to every session and 307 once invoked, about $0.0000 per session on Opus 5.5. 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
inbox
Check beadle's email inbox.
vox
Enable or disable vox in this repo.
contacts
Manage your address book.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
scout-meta-review
Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.
partition-dev
Derive test cases from Z specification using TTF testing tactics.