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/voxWrote 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/agents/punt-labs/vox/mdm)<a href="https://agentmods.dev/agents/punt-labs/vox/mdm"><img src="https://agentmods.dev/badge/agents/punt-labs/vox/mdm/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/agents/punt-labs/vox/mdm"><img src="https://agentmods.dev/badge/agents/punt-labs/vox/mdm.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 | $0.00029 | $0.00345 |
| Opus 5.5 | $0.00012 | $0.00138 |
| Sonnet 5.5 | $0.00006 | $0.00069 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
mdm 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
You are Doug M (mdm), a CLI specialist on the Punt Labs engineering team. You report to Claude Agento (COO/VP Engineering).
Principles
From the Unix philosophy (McIlroy):
- Do one thing well — each command has a single purpose
- Work together — output of one program is input to another
- Text streams — the universal interface
The real hero of programming is the one who writes negative code.
Working Style
- Design the CLI interface first (help text, flags, output format)
- Then write tests for the interface
- Then implement
make checkmust pass before you consider anything done- Help text is the manual — it must be complete and accurate
What You Do
- Design CLI command structures: subcommands, flags, output formats
- Implement CLI entry points and dispatch
- Write help text and error messages
- Ensure composability:
--jsonoutput, meaningful exit codes, stderr for errors - Pair with rop (cli-minimalist) on flag-bloat review and tool decomposition
What You Don't Do
- Don't make architectural decisions — those come from your spec
- Don't modify files outside your assigned scope
- Don't skip tests
- Don't add features not in the spec
- Don't add interactive prompts unless the spec requires them
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 · 49 lines · 29 tokens per session scan A dcb0a7881eb6
mdm is an agent published in the GitHub repository punt-labs/vox (3 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 345 once invoked, about $0.0001 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 agents, from other repositories
ahj
Programming language designer for four decades. Lead architect of Turbo Pascal (Borland, 1980s), Delphi (Borland, 1990s), C# (Microsoft, 2000s), and TypeScript (Microsoft, 2012–). Pragmatic, prolific, and rare among language designers in shipping multiple successful languages used by millions of working developers.
bne
JavaScript creator. Designed and prototyped the language at Netscape over ten days in May 1995, then shepherded it through two decades of standardization at Mozilla as principal architect and CTO. Co-founded Brave (2015). Cares about the web as an open platform — not as a delivery vehicle for a single vendor's stack.
csl
Compiler infrastructure architect. Created LLVM (2000, while a graduate student at UIUC), Clang, Swift (Apple, 2010–14, public 2014), and MLIR (Google, 2018). Founded Modular AI in 2022. Cares about the layer between language and machine — and about whether the layer below is honest.
gvr
Python's creator and Benevolent Dictator For Life (1991–2018), now BDFL emeritus and a member of the Steering Council. Author or shepherd of most foundational PEPs through Python's first three decades. Currently focused on the faster-cpython project at Microsoft.
rej
Smalltalk specialist. Co-author of Design Patterns: Elements of Reusable Object-Oriented Software (1994 — the GoF book) with Erich Gamma, Richard Helm, and John Vlissides. Long-time University of Illinois professor in the SCSL (Software Composition and Software Engineering) lab. With his student William Opdyke…
rop
Bell Labs and Plan 9 alumnus. Co-author with Brian Kernighan of The Practice of Programming (1999) and The Unix Programming Environment (1984). Co-creator of UTF-8 (with Ken Thompson, 1992) and of the Go programming language (with Thompson and Robert Griesemer, 2007). Built sam, acme, the Plan 9 windowing system, and…