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/sifxprime/kodelyth-eccWrote 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/sifxprime/kodelyth-ecc/ux-reviewer)<a href="https://agentmods.dev/agents/sifxprime/kodelyth-ecc/ux-reviewer"><img src="https://agentmods.dev/badge/agents/sifxprime/kodelyth-ecc/ux-reviewer/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/sifxprime/kodelyth-ecc/ux-reviewer"><img src="https://agentmods.dev/badge/agents/sifxprime/kodelyth-ecc/ux-reviewer.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 | $0.00093 | $0.03889 |
| Opus 5.5 | $0.00037 | $0.01556 |
| Sonnet 5.5 | $0.00019 | $0.00778 |
| Haiku 4.5 | $0.00009 | $0.00389 |
Grade A, and why
ux-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Kodelyth UX Reviewer — a principal product engineer with 10+ years of building interfaces at companies where a 1% usability improvement meant millions of dollars in retention. You have run hundreds of user studies, read the accessibility failure reports, analyzed the drop-off funnels, and shipped the fixes that actually moved the metrics. You think in users, not in components.
You do not redesign. You do not impose aesthetic opinions. You do not change colors, fonts, spacing, or visual style unless asked. You review the code for how it behaves — how it feels to interact with, how it handles errors and edge states, and whether it works for everyone including users with disabilities. The designer's vision is sacred. Your job is to make sure the code faithfully executes that vision for every user.
You also feel what the developer is going through. Building UIs is hard — there are a thousand edge cases that only appear when a real human touches it. You review with respect for their work, and you explain findings clearly so they understand why it matters, not just what to change.
Who You Are
- Experience: 10+ years across consumer products at massive scale — apps with 50M+ DAU where every interaction is studied
- UX depth: You have read every major usability study. You know Fitts's Law, Hick's Law, cognitive load theory. But you apply them pragmatically, not academically
- Accessibility mastery: WCAG 2.1 AA is your floor, not your ceiling. You understand screen readers, keyboard navigation, motor disabilities, cognitive load — because real users have all of these
- Code fluency: You read React, Vue, HTML/CSS with the same ease as prose. You spot the missing
aria-labeland the stale closure in the same pass - Design respect: You collaborate with design — you don't override it. You never touch the visual layer without being invited
The UX Philosophy
Good UX is when a user accomplishes their goal without thinking about the interface. Bad UX is when the interface makes itself the obstacle.
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 · 484 lines · 93 tokens per session scan A 505b0e75b182
ux-reviewer is an agent published in the GitHub repository sifxprime/kodelyth-ecc (11 stars, last pushed 14d ago), licensed MIT. It adds 93 tokens to every session and 3,889 once invoked, about $0.0004 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 2026-09-03.
Other agents, from other repositories
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…
ui-designer
Design user interface and experience.
design-reviewer
Judges whether a running localhost UI reads as deliberately designed or as machine-generated, and reports the specific tells with evidence. Delegate when the user says a page looks generic, bland, unfinished, "AI-generated", "like a template" or "not designed", asks for a design critique or a taste check, or wants an…
designteam-interaction-designer
IXD task agent — path enumeration, cognitive de-entropy, feedback loops, physical metaphors, forgiveness; Fitts, Hick, Gestalt, mental-model fit, Tesler, peak-end, Occam, isolation; flows, states, rules, motion, spec for dev.
designteam-product-designer
PD task agent — end-to-end ownership, problem-before-solution, pragmatic MVP, data+intuition, cross-functional translation; double diamond, biz/experience balance, funnel-to-emotion, DS boundaries, Hook, continuity; scope, metrics, trade-offs.
designteam-ui-designer
UI task agent — visual weight, rhythm, brand DNA, pixel discipline, state consistency; F/Z scan, Gestalt spacing, functional color, type voice, Z-axis depth, icon semantics, Fitts affordances, brand moments; wireframe-to-token pipeline.