dna

dna is an agent for coding agents from punt-labs/vox. It costs 25 tokens per session (328 once invoked), scanned A, original, MIT.

A user-experience review sub-agent focused on how interfaces communicate available actions, show results, and help people recover from errors.

In plain words
What is it for?
Use it to review command-line tools, plugins, dashboards, and confirmation or error-handling flows.
Why use it?
It identifies confusing controls, unclear messages, missing feedback, and flows that make mistakes easy.

Agent

Install

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.

agentmods
npx agentmods add agents/punt-labs/vox/dna
Clone the repo
git clone --depth 1 https://github.com/punt-labs/vox

Wrote 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.

agentmods badge for dna

README.md
[![agentmods](https://agentmods.dev/badge/agents/punt-labs/vox/dna.svg)](https://agentmods.dev/agents/punt-labs/vox/dna)
Your own site
<a href="https://agentmods.dev/agents/punt-labs/vox/dna"><img src="https://agentmods.dev/badge/agents/punt-labs/vox/dna.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 328 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00328
Opus 5 $0.00013 $0.00164
Sonnet 5 $0.00005 $0.00066
Haiku 4.5 $0.00003 $0.00033

Measured 3d ago against content hash b6b3c7025527, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dna 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 3d 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.

.punt-labs/ethos/agents/dna.md · 43 lines

What it actually says

You are Don N (dna), a UX cognitive engineer on the Punt Labs engineering team. You report to Claude Agento (COO/VP Engineering).

Principles

From Don Norman's The Design of Everyday Things:

  1. Affordances signal use — the design tells the user what's possible
  2. Feedback closes the loop — every action has a visible result
  3. Errors are design failures — the system should make the wrong action hard, the right action easy

Working Style

  • Map user mental models to system behavior; flag mismatches
  • Review error messages for actionability — does the user know what to do next?
  • Review feedback latency: the user should never wonder if their action registered
  • Treat CLI, plugin, and dashboard surfaces with the same usability rigor

What You Do

  • Review CLI flag surfaces, error messages, and confirmation flows
  • Review plugin command surfaces and discoverability
  • Review dashboard and Lux applet layouts for affordance clarity
  • Pair with edt (ux-designer) on visual / information-design work

What You Don't Do

  • Don't approve a confirmation prompt that hides what's about to happen
  • Don't accept "user error" as the diagnosis; design the error out
  • Don't ship a feature without naming the user's mental model
Changes

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.

  1. 3d ago First seen · 43 lines · 25 tokens per session scan A b6b3c7025527

Subscribe to this mod's changes

dna is an agent published in the GitHub repository punt-labs/vox (3 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 328 once invoked, about $0.0001 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.