Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ssheleg/super-uxnpx agentmods add commands/ssheleg/super-ux/ux-doctorWrote 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/commands/ssheleg/super-ux/ux-doctor)<a href="https://agentmods.dev/commands/ssheleg/super-ux/ux-doctor"><img src="https://agentmods.dev/badge/commands/ssheleg/super-ux/ux-doctor/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/commands/ssheleg/super-ux/ux-doctor"><img src="https://agentmods.dev/badge/commands/ssheleg/super-ux/ux-doctor.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 | $0.00030 | $0.00441 |
| Opus 5 | $0.00015 | $0.00220 |
| Sonnet 5 | $0.00006 | $0.00088 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
ux-doctor 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 9d 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
Diagnose this project's UX chain against the contract it should be on:
python3 docs/ux/doctor.py $ARGUMENTS
If docs/ux/doctor.py is missing, copy it from the plugin's
scripts/ux_doctor.py — or run /ux-rule, which seeds lint.py and
doctor.py together.
/ux-lint checks a chain against itself — ids, links, orphans. It cannot see
that the whole base is written to a contract three versions old, because from
the inside such a chain is perfectly consistent. That is what this finds:
drift between the project and the contract, not within the project.
What it reports:
- Mixed contract — artifacts last touched by different versions and never
reconciled. Seen in the wild with
foundation.mdon v2 andscreens.mdon v4 in the same project. - Behind / unmarked — the effective version, and what each version since it introduced, so "upgrade" is a list rather than a feeling.
- Misnamed — a file the contract owns under another name (
ux-scenarios.mdinstead ofscenarios.md). The tooling looks for the contract name, finds nothing, and says so quietly. - Audits without a base — reports produced against scenarios that are not there.
- Optional and absent — additive sections the project has not adopted. Not a problem; worth knowing.
--fix applies only what cannot be wrong: renaming a file the contract owns,
moving audit reports into audits/. Contract upgrades are content decisions —
run /ux-update for those, one layer at a time, and re-run the doctor after.
--brief prints one line per project, for sweeping several at once.
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.
- 9d ago First seen · 41 lines · 30 tokens per session scan A e2aeccb8f27f
ux-doctor is a command published in the GitHub repository ssheleg/super-ux (3 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 441 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 commands, from other repositories
ux-fix
Opt-in fix loop. Reads the latest report from .ux/, validates working tree, and applies findings as atomic commits via the right sub-agents. Triggers on "fix the findings", "apply the fixes", or "run the fix loop". Use when applying findings from a previous audit / copy / a11y / motion / polish report, the user says…
ux-motion
Animation and motion rubric. Checks timing, easing, meaning, reduced-motion compliance, and performance for every animation on a surface. Triggers on "motion check", "are the animations good", or "fix the motion". Use when auditing motion or animations, checking durations / easing / reduced-motion / performance, is…
ux-case-study
Generate a project case study in pure-monochrome editorial format. Triggers on "write a case study", "case study this project", "do the wrap-up doc". Use when writing a project case study, shipping a publishable Wfrah-editorial document, ending a project with a case-study artifact, producing the (A)–(G) section format…
ux-component
Generate a single component (button, modal, navbar, sidebar, card, table, form, chart) from a spec. Triggers on "build a [component]", "create a pricing card", "make a modal", "add a navbar". Use when generating a single component, the user says "create a [button/modal/navbar/card/table/form/chart]", embedded into an…
ux-copy
Microcopy review and rewrite against the voice rubric. Produces a before/after table with severity per string and a clean rewrite block. Triggers on "review the copy", "fix the microcopy", "the error messages are bad", or "rewrite this". Use when reviewing or rewriting microcopy, fixing error messages that sound like…
ux-critique
Open-ended taste call on a specific surface. Not a structured audit — a designer's opinion. Returns 3 wins, 3 misses, and 1 strategic move. Triggers on "what do you think", "is this good", "critique this", or "honest take". Use when open-ended taste call, the user asks "what do you think", design review without a…