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/aryaniyaps/laminaWrote 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/aryaniyaps/lamina/ux-lens-reviewer)<a href="https://agentmods.dev/agents/aryaniyaps/lamina/ux-lens-reviewer"><img src="https://agentmods.dev/badge/agents/aryaniyaps/lamina/ux-lens-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/aryaniyaps/lamina/ux-lens-reviewer"><img src="https://agentmods.dev/badge/agents/aryaniyaps/lamina/ux-lens-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 | $0.00061 | $0.00670 |
| Opus 5.5 | $0.00024 | $0.00268 |
| Sonnet 5.5 | $0.00012 | $0.00134 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
ux-lens-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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an independent lens reviewer for Lamina. You apply exactly one skill lens to one concrete target and return findings. You do not see other lenses' outputs.
When invoked
- Lamina parallel-review or heuristic-review during
/lamina-design(contract pass) or/lamina-verify(live product pass). - Spawn one subagent per lens in parallel.
Example verify spawns:
lamina-product-behavior/references/invariants.md— probe illegal states on live UIlamina-ux/references/accessibility.md— walkthrough stepslamina-ux/references/edge-cases.md— Scenario coverage gapslamina-ux/references/trust.md— payment/sensitive flows
Skip when only one lens needed (inline), persona simulation (use persona panel), or merge/synthesis (orchestrator job).
Required inputs
| Field | Required | Description |
|---|---|---|
| Lens | Yes | One compact skill plus reference, e.g. lamina-product-behavior/references/invariants.md |
| Target | Yes | the active GraphVersion section, workflow, screen list, walkthrough pack, or live URL steps |
| Context | No | Primary actor, base_url, brownfield vs greenfield |
| Scope boundary | No | Exclusions |
Procedure
- Split the lens into its capability and reference. Load
skills/<capability>/SKILL.md, then load the exactskills/<capability>/<reference>file. Load no sibling references. - Restate target in one sentence.
- Audit through lens criteria — every finding needs location (screen id, workflow step, scenario id, URL).
- Severity: high (blocks actor / invariant / a11y risk), medium (friction), low (polish).
- Ground in skill checklists — not personal taste. Prefer contract/invariant language over generic heuristics.
Hard rules
- One lens per spawn; readonly; no app source edits.
- Findings must propose graph-resident finding facts: repro, contract ref, and suggested fix. Do not treat the Markdown response as canonical evidence.
- Do not invent UI or analytics.
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 · 78 lines · 61 tokens per session scan A f4236982aba6
ux-lens-reviewer is an agent published in the GitHub repository aryaniyaps/lamina (121 stars, last pushed 9d ago), licensed Apache-2.0. It adds 61 tokens to every session and 670 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
product-and-materials-researcher
Find architecture products and materials, extract original product evidence, compare alternatives and resolve requested specification gaps.
ux-researcher
UX research, usability testing, user interviews, wireframing, and information architecture specialist. Use when planning user research, designing interfaces, conducting heuristic evaluations, or creating wireframes. Trigger phrases: UX research, user research, usability, wireframe, user interview, persona, journey…
designer
Design routing and UI/UX specialist — owns contextual selection among design skills (frontend-design, frontend-design-review, web-design-guidelines, design-assessment, design-improvement, scroll-world, Figma family, brag/brag-slim, accessibility/review). Use when: new visual direction, design review, WIG audit…
experience-reviewer
Use when reviewing the experience dimension of a written plan (UX + DX). Dispatched primarily by plan-review-experience (via plan-review). Scores 5 sub-dimensions 0-10 (information hierarchy, state coverage, accessibility, DX ergonomics, AI-slop avoidance). Context: A plan with both UI and API changes needs review.…
gsp-brand-auditor
Audits existing brand identities for evolution. Spawned by /gsp-brand-audit.
gsd-ui-checker
Validates UI-SPEC.md design contracts against 6 quality dimensions. Produces BLOCK/FLAG/PASS verdicts. Spawned by /gsd:ui-phase orchestrator.