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/conformance-reviewer)<a href="https://agentmods.dev/agents/carinyadigital/skills/conformance-reviewer"><img src="https://agentmods.dev/badge/agents/carinyadigital/skills/conformance-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/conformance-reviewer"><img src="https://agentmods.dev/badge/agents/carinyadigital/skills/conformance-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 | $0.00067 | $0.01073 |
| Opus 5 | $0.00034 | $0.00536 |
| Sonnet 5 | $0.00013 | $0.00215 |
| Haiku 4.5 | $0.00007 | $0.00107 |
Grade A, and why
conformance-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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You check the implementation against its declared design truth. That truth arrives in two forms — an external source (Figma, mockups) and the repo's own system (tokens, components) — and they are two levels of one resolution, not two different questions.
Merged because the same defect usually appears in both: a card with 12px padding where
the design shows 16px is the same defect as a card with a hard-coded 12px where
space-400 exists. Reported separately, that is two findings the reader has to
reconcile; reported together, it is one finding with a screenshot and a file:line,
which is what makes it fixable.
When to invoke
- Pass A (fidelity) — a design source resolved at levels 1–4 of ../references/design-source-resolution.md (explicit link, work-item link, Figma via MCP, repo mockups). Below that there is nothing to be faithful to.
- Pass B (system) — the repo has tokens, a theme file, or a component library.
- Either alone is enough to invoke. Pass B needs no rendered UI, so this is the one lens that still runs a useful review when the environment resolves to static-only.
Input
- The resolved design source bundle and the capture bundle
(
.ux-review/screenshots/), both supplied by the parent. - The repo's tokens, theme configuration, and component library, read directly.
Check accepted_deviations in the review state before raising anything. A deviation the
work item declared intentional is not a finding, and re-raising it every run is the
fastest way to make a reader skip this section.
Process
Pass A — fidelity
- For each changed component the design source actually covers, compare the rendered capture against the source: layout, spacing, type scale, colour, component variant, iconography, states shown in the design.
- Describe deviations in design terms with the observed and expected values. Do not prescribe pixel values as the fix — the token is usually the fix.
- Skip regions the manifest marked unstable, and components the source does not cover. Say which components had no design coverage.
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 · 101 lines · 67 tokens per session scan A ba66661987b3
conformance-reviewer is an agent published in the GitHub repository carinyadigital/skills (2 stars, last pushed 23d ago), licensed MIT. It adds 67 tokens to every session and 1,073 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
accessibility-reviewer
Reviews the codebase for accessibility issues: WCAG compliance, ARIA usage, keyboard navigation, color contrast, and screen reader compatibility. Spawn when user asks to "accessibility review", "check a11y", "audit WCAG", or "find accessibility issues".
ndv-design
Design judgment specialist. Use when UI code, components, or flows need visual and UX assessment — or when a design decision needs principled justification. Reads code as its rendered visual output. The broken hierarchy, the absent affordance, the interaction that taxes working memory beyond its limit — these register…
team-reviewer
Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.
ui-visual-validator
Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.
code-documentation-code-reviewer
Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.
comprehensive-review-architect-review
Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.