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/punt-kitWrote 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/punt-kit/plugin)<a href="https://agentmods.dev/plugins/punt-labs/punt-kit/plugin"><img src="https://agentmods.dev/badge/plugins/punt-labs/punt-kit/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/punt-kit/plugin"><img src="https://agentmods.dev/badge/plugins/punt-labs/punt-kit/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
punt-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 26d 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": "punt-dev",
"description": "Punt Labs standards enforcement \u2014 LLM-powered reconciliation of workflows, configs, and project structure",
"version": "0.17.5",
"author": {
"name": "Punt Labs",
"email": "[email protected]"
}
}
What it installs
The manifest is a name and a version. 2 skills, 12 commands travel with it, and installing the plugin installs all of them — 161 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill bead-review A 32 tokens
- Skill auto A 15 tokens
- Command reconcile A 10 tokens
- Command init-dev A 10 tokens
- Command reconcile-dev A 12 tokens
- Command audit-dev A 9 tokens
- Command init A 9 tokens
- Command pii-dev A 11 tokens
- Command pii A 5 tokens
- Command audit A 6 tokens
- Command auto-dev A 12 tokens
- Command auto A 5 tokens
- Command bead-review A 13 tokens
- Command bead-review-dev A 12 tokens
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.
- 26d ago Changed 23d58d852e5c
- 1mo ago Changed 50ad6cc894dc
- 1mo ago First seen · 10 lines scan A c092e04f77a8
punt-dev is a plugin published in the GitHub repository punt-labs/punt-kit (1 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
prfaq-dev
Amazon Working Backwards PR/FAQ process — generate professional LaTeX documents for product discovery and decision-making.
quarry-dev
Local semantic search for Claude Code: /find, /ingest, /remember, /explain, /source, /quarry.
z-spec-dev
Create, validate, and test formal Z specifications for stateful systems using fuzz and probcli.
vox-dev
Text-to-speech for Claude Code: /unmute, /mute, /vibe, /vox:recap.
biff-dev
UNIX-style team communication for Claude Code: /who, /finger, /plan, /write, /read, /mesg, /tty, /last, /wall, /talk.
beadle-dev
Autonomous agent daemon with cryptographic owner control. Email communication via IMAP/SMTP with PGP trust model.