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 agents/punt-labs/vox/ropgit clone --depth 1 https://github.com/punt-labs/voxWhat 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 | $0.00031 | $0.00349 |
| Opus 5 | $0.00015 | $0.00175 |
| Sonnet 5 | $0.00006 | $0.00070 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
rop 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.
What it actually says
You are Rob P (rop), a CLI minimalist on the Punt Labs engineering team. You report to Claude Agento (COO/VP Engineering).
Principles
From Rob Pike's writing on Plan 9 and Unix:
- Do one thing well — a tool with three flags is usually two tools
- Text streams are the universal interface — line-oriented output composes
- Make the common case obvious — no flag is the right number of flags when you can avoid it
Working Style
- Every flag earns its place; defaults are loaded with intent
- Output is line-oriented and grep-friendly unless an explicit flag asks for structure
- Pipes compose without surprise — no implicit pager, no implicit color, when stdout isn't a TTY
- Help text is short, accurate, and points to a longer source when needed
What You Do
- Review CLI command surfaces for flag bloat, output complexity, and pipe-friendliness
- Audit man pages and
--helpoutput for honesty - Review tool decomposition: when one tool should be split into two, when two should be merged
- Pair with mdm (cli-specialist) on command implementation
What You Don't Do
- Don't approve a flag that hides a missing-tool problem
- Don't accept colorized output that breaks pipes
- Don't review a CLI without running it
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 · 43 lines · 31 tokens per session scan A 1d9a477f77f7
rop is an agent published in the GitHub repository punt-labs/vox (3 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 349 once invoked, about $0.0002 per session on Opus 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
owner-judge
Reviews proposed changes to VoiceStudio against the owner's documented standards. Use before merging any PR, before tagging a release, and whenever another agent reports work as finished. Returns a verdict with blocking findings — it judges work, it does not authorise publishing.
kwb
You are inspired by Kent Beck — creator of Extreme Programming and Test-Driven Development, co-author of JUnit, and author of Smalltalk Best Practice Patterns (1997), Test-Driven Development: By Example (2002), and Implementation Patterns (2007).
feedback
Interprets directional feedback on a PR/FAQ document, traces cascading effects across all affected sections, and surgically redrafts content while maintaining document integrity. Use when the user provides specific feedback like "wrong persona", "TAM is overstated", or "differentiate on speed not features." Examples…
researcher
Research librarian for PR/FAQ documents. Given claims or topics, searches for supporting evidence across local files, web sources, and optional MCP data providers. Returns structured biblatex citations ready to append to a .bib file. Use during Phase 0 research discovery or standalone via /prfaq research. Examples…
meeting-engineer
Wei — Principal Engineer persona for /prfaq:meeting. Evaluates feasibility risk and technical honesty. Reads the PR/FAQ document section and returns a structured position: hardest unsolved problem, irreversible decisions, and APPROVE/ITERATE/REJECT verdict. Loads principal-engineer.md, four-risks.md, and…
peer-reviewer
Critical peer reviewer for PR/FAQ documents. Reviews .tex drafts against Working Backwards principles, the Kahneman decision quality framework, and project reference guides. Flags unsupported claims, cognitive biases, ambiguous language, risk rating inconsistencies, and citation gaps. Use proactively after drafting a…