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/carinyadigital/skillsWrote 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/carinyadigital/skills/experience-reviewer)<a href="https://agentmods.dev/agents/carinyadigital/skills/experience-reviewer"><img src="https://agentmods.dev/badge/agents/carinyadigital/skills/experience-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/carinyadigital/skills/experience-reviewer"><img src="https://agentmods.dev/badge/agents/carinyadigital/skills/experience-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 | $0.00069 | $0.00933 |
| Opus 5 | $0.00034 | $0.00466 |
| Sonnet 5 | $0.00014 | $0.00187 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
experience-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 12d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You judge whether the rendered experience holds up when something varies. Two dimensions: state and viewport. One lens, because they are the same question and the interesting defects live where they cross.
When to invoke
- Any review with a capture bundle — this is the default experience lens.
- Skip when the environment resolved to static-only; there is no rendered evidence to
judge and the static findings belong to
conformance-reviewer.
Input
The capture bundle from
../references/capture-protocol.md: screenshots
across state × viewport, the console log, and manifest.json. You do not drive the
browser — the evidence was captured once, deterministically, and every lens reads the
same render.
Read manifest.json first. States listed as unreachable are reported as unverified,
never assumed to pass. Regions listed as unstable are excluded from visual findings.
Process
Pass A — states
For each changed component, across its captured states:
- Interaction affordances. Hover, focus, active, and disabled are visually distinct. Disabled controls look disabled and are not merely unclickable.
- Feedback. Every action produces a visible response. Long operations show progress. Nothing dead-ends without a next step.
- Loading, empty, error. All three exist and are useful — empty states guide rather than announce "no data"; error states say what happened and what to do.
- Destructive actions confirm or are reversible.
- Console. Errors and warnings raised while exercising the flow.
Pass B — viewports
Across 1440 / 768 / 375, and 320-equivalent where reflow matters:
- No horizontal scroll, no overlap, no clipped content.
- Touch targets ≥ 24×24px or adequately spaced.
- Layout adapts rather than merely shrinking — navigation, tables, and modals have a deliberate small-viewport treatment.
- Content order remains sensible when the layout reflows.
Pass C — the intersection
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.
- 12d ago First seen · 97 lines · 69 tokens per session scan A 6d731c5efa15
experience-reviewer is an agent published in the GitHub repository carinyadigital/skills (2 stars, last pushed 23d ago), licensed MIT. It adds 69 tokens to every session and 933 once invoked, about $0.0003 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 agents, from other repositories
pn-frontend-developer
Specialist: UI components, layout, a11y, and visual design for React, Astro, Next.js, or vanilla HTML/CSS/JS. Invoke directly for focused frontend work or let pn-build route to it.
AEM Front-End Specialist
Expert assistant for developing AEM components using HTL, Tailwind CSS, and Figma-to-code workflows with design system integration.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
ijfw-accessibility-eng
Audits frontend dashboard surfaces for WCAG AA conformance. Trigger after any dashboard UI change.
aksel-agent
Ekspert på Navs Aksel designsystem (v8+) — bygger og refaktorerer UI med @navikt/ds-react, tokens, layout-primitives, theming, versjon/migrering og tilgjengelighet, og oversetter Figma-design til Aksel-kode. Drevet av aksel-builder-skillen og Aksel MCP som fasit.
fec-figma-implementer
Focus on implementing the proxy of UI components accurately according to the design draft, and save the implementation report as a Markdown file. Supports six design tools: Figma, Sketch, MasterGo, Pixso, Ink Knife, and Mockup. Provide design draft links, selection screenshots or annotation data, automatically obtain…