Borrowing it
Nothing to install: this file belongs to dork-labs/dorkos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dork-labs/dorkos/main/.agents/skills/auditing-ui/SKILL.mdgit clone --depth 1 https://github.com/dork-labs/dorkosWrote 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/skills/dork-labs/dorkos/auditing-ui)<a href="https://agentmods.dev/skills/dork-labs/dorkos/auditing-ui"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/auditing-ui/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/skills/dork-labs/dorkos/auditing-ui"><img src="https://agentmods.dev/badge/skills/dork-labs/dorkos/auditing-ui.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 | $0.00115 | $0.06059 |
| Opus 5.5 | $0.00046 | $0.02424 |
| Sonnet 5.5 | $0.00023 | $0.01212 |
| Haiku 4.5 | $0.00012 | $0.00606 |
Grade A, and why
auditing-ui 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing UI
An audit reads the interface through several independent lenses at once, then merges what they saw into one ranked report and a set of PR-sized batches. It writes zero code.
The rules live in the charter, not here: audits/ui.md (domain) inherits audits/README.md
(cross-domain). What passes lives in contributing/design-review.md: the numbered rules a
finding cites and the floors the browser leg measures. The charter is the authority on the lens set, the lens keys, and which lens is
surface-local versus whole-tree. This file is the procedure, and it is the single home for
the procedure: the commands under /ui-audit:* point here rather than restating any of it.
Read the charter before every run. If audits/ui.md is missing, run /ui-audit:init first.
1. Durable state
Three things outlive any single run and live at the domain root, audits/runs/ui/:
| Path | What | Written by |
|---|---|---|
profile.md |
how work lands in this repo | /ui-audit:init |
stamps.json |
per-lens last-audited commit + rotation cursor | run and pulse |
<date>/ |
one run's report.md, raw/<key>.md, and its ledger when untracked |
run and pulse |
<date> is ISO YYYY-MM-DD.
The repo profile is consulted, not decorative
Read audits/runs/ui/profile.md at the start of every run, pulse, and execute. It answers
questions this procedure deliberately does not hard-code, and each answer changes behavior:
- Landing style — a repo with no merge queue must not inherit arm-then-verify or a bare
gh pr merge --auto;executefollows the profile's answer, not this repo's habits. - Changelog — whether a batch owes a fragment, and in what shape.
- Isolation — worktree per batch, or something else.
- Formatting gate — the exact command that satisfies CI, run last before every push.
- Tracker mode — the adapter path in §5, or the markdown ledger.
- Browser leg — the dev command and a free port, or the fact that there is none, which is what §3's degrade rule keys off.
What ships with it
13 files beside SKILL.md 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.
- assets/auditor-prompt.md 3.3 KB
- assets/measure/floors.json 1.2 KB
- assets/measure/focus-walk.mjs 4.4 KB runs code
- assets/measure/guards.mjs 1.6 KB runs code
- assets/measure/guards.test.mjs 3.2 KB runs code
- assets/measure/in-page.mjs 17 KB runs code
- assets/measure/measure.mjs 9.8 KB runs code
- assets/measure/report.mjs 3.5 KB runs code
- assets/reference-implementation/README.md 1.6 KB
- assets/reference-implementation/ui-ux-audit.js 14 KB runs code
- assets/reference-implementation/uiux-wave.js 13 KB runs code
- assets/review-brief.md 2.3 KB
- assets/synthesizer-prompt.md 2.2 KB
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.
- today Changed · +65 lines · +35 tokens per session 62b88038ed6c
- 29d ago Changed · +1 lines 9c8459d622cc
- 1mo ago First seen · 304 lines · 80 tokens per session scan A d4ce0eeb221d
auditing-ui is a skill published in the GitHub repository dork-labs/dorkos (12 stars, last pushed today), licensed MIT. It adds 115 tokens to every session and 6,059 once invoked, about $0.0005 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 2026-09-08.
Other skills, from other repositories
hive.colony-progress-tracker
Claim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn message includes a dbpath field.
design-inventory
Use to run the Claude Design to ClosedLoop pipeline against the current web-ui. Stage A inventories a design export zip into schema-validated findings (typed design units - screens, regions like nav bars, standalone components like a chat dialog; UX and behavioral changes; Storybook component reuse mapping; token…
project-planner
Detailed implementation plans and spec-driven development.
remote-screenshot
Take a real screenshot of a running Neovim from inside the Claude Code on the web container, which has no X server. Use when asked to show what a UI change looks like, or to attach an image of the chat buffer, a split layout, an approval prompt or a picker. Requires CLAUDECODEREMOTE=true — on a local machine there is…
scout-briefing
Launch a Scout morning briefing session as a background process. Auto-detects mode (morning briefing, consolidation, or weekend briefing) from the current time and day.
scout-dream
Launch a Scout dreaming session as a background process. Processes feedback, does KB deep work, and works on wishlist items.