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/plugins/punt-labs/biff/plugin)<a href="https://agentmods.dev/plugins/punt-labs/biff/plugin"><img src="https://agentmods.dev/badge/plugins/punt-labs/biff/plugin/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/plugins/punt-labs/biff/plugin"><img src="https://agentmods.dev/badge/plugins/punt-labs/biff/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
biff-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.
What it actually says
{
"name": "biff-dev",
"description": "UNIX-style team communication for Claude Code: /who, /finger, /plan, /write, /read, /mesg, /tty, /last, /wall, /talk",
"version": "1.19.0",
"author": {
"name": "Punt Labs",
"email": "[email protected]"
},
"mcpServers": {
"tty": {
"type": "stdio",
"command": "biff",
"args": [
"mcp"
]
}
}
}
What it installs
The manifest is a name and a version. 22 commands, 2 agents, 6 hooks travel with it, and installing the plugin installs all of them — 318 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command read-dev A 6 tokens
- Command talk A 10 tokens
- Command talk-dev A 10 tokens
- Command wall-dev A 6 tokens
- Command finger A 10 tokens
- Command finger-dev A 10 tokens
- Command last A 5 tokens
- Command last-dev A 5 tokens
- Command biff-dev A 8 tokens
- Command plan A 28 tokens
- Command plan-dev A 28 tokens
- Command tty-dev A 13 tokens
- Command who A 9 tokens
- Command who-dev A 9 tokens
- Command write-dev A 6 tokens
- Command mesg A 3 tokens
- Command mesg-dev A 3 tokens
- Command read A 6 tokens
- Command wall A 6 tokens
- Command biff A 8 tokens
- Command tty A 13 tokens
- Command write A 6 tokens
- Agent distributed-test-engineer A 61 tokens
- Agent leak-hunter A 49 tokens
- Hook PreToolUse A not measured
- Hook UserPromptSubmit A not measured
- Hook PostToolUse A not measured
- Hook SessionStart A not measured
- Hook SessionEnd A not measured
- Hook PreCompact A not measured
What ships with it
3 files beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed 52ba7eaebb3d
- 1mo ago Changed 418433412900
- 1mo ago Changed 637ede80dd31
- 1mo ago First seen · 19 lines scan A fa71ba47c5b3
biff-dev is a plugin published in the GitHub repository punt-labs/biff (2 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
ponytail
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
i-have-adhd
Shape Claude Code output for an ADHD reader: lead with the next action, number steps, suppress tangents, restate state, make wins visible.
dev-skills
Lightweight skills for users with existing workflows - coding best practices, testing principles, and design guidelines without recipe workflows or agents.
handbook
Core Claude Code handbook with best practices and essential tools.
hush
Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.
super-token-saver
45% cost reduction measured. Cache expiry prevention, SubTask auto-delegation, zero-cost context restoration, real-time cost dashboard. The only Claude Code plugin built from CC source analysis.