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.
npx skills add ils15/pantheon-legacy --skill visual-review-pipelinegit clone --depth 1 https://github.com/ils15/pantheon-legacyWrote 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/skills/ils15/pantheon-legacy/visual-review-pipeline)<a href="https://agentmods.dev/skills/ils15/pantheon-legacy/visual-review-pipeline"><img src="https://agentmods.dev/badge/skills/ils15/pantheon-legacy/visual-review-pipeline/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/skills/ils15/pantheon-legacy/visual-review-pipeline"><img src="https://agentmods.dev/badge/skills/ils15/pantheon-legacy/visual-review-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.01825 |
| Opus 5 | $0.00016 | $0.00912 |
| Sonnet 5 | $0.00006 | $0.00365 |
| Haiku 4.5 | $0.00003 | $0.00183 |
Grade A, and why
visual-review-pipeline 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 8d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Review Pipeline
Automated visual review: Aphrodite captures screenshots via Playwright MCP → Self-analyzes for visual issues → Addresses findings in a loop.
Overview
This pipeline establishes a formal workflow for detecting and resolving visual regressions and design issues. It enforces structured JSON output, iteration limits, and escalation criteria to prevent infinite fix loops.
Pipeline Flow
Aphrodite implements UI
↓
Playwright screenshot (browser/screenshotPage)
↓
Aphrodite self-analyzes (layout, contrast, responsive, accessibility)
↓
├─ verdict: pass → proceed to Themis review
├─ verdict: fail + iteration < 3 → fix → re-capture
└─ verdict: fail + iteration = 3 → Zeus escalation
Workflow Steps
Step 1: Capture
Aphrodite uses Playwright MCP to capture screenshots.
- Navigate to target URL or render component
- Capture full-page screenshot via
browser/screenshotPage - Capture viewport-specific screenshots for responsive checks
- Name files descriptively:
screenshot-iteration-N-component.png
Step 2: Analyze
Aphrodite self-analyzes screenshots visually.
- Examine screenshot(s) for visual issues
- Identify problems in layout, contrast, responsive behavior, and accessibility
- Return findings in the structured JSON schema (below)
- Include iteration number in findings
- Mark issues with
pass_if_fixedIDs
Step 3: Fix
Aphrodite addresses each finding from self-analysis.
- Triage findings by severity (critical → high → medium → low)
- Fix each issue in component code
- Commit changes with descriptive message
- Re-capture screenshot for next iteration
Step 4: Loop
Repeat Steps 1-3 for up to 3 iterations.
- Each iteration must fix at least one
pass_if_fixedissue - Track iteration count in findings object
- If no progress detected (zero fixes applied), escalate immediately
- Compare before/after screenshots to verify fixes
Step 5: Escalate
Zeus intervenes if issues persist after 3 iterations.
- Trigger: 3 iterations exhausted or zero-progress detected
- Action: Zeus coordinates manual review or architectural decision
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.
- 8d ago First seen · 201 lines · 32 tokens per session scan A f6e65ff75a93
visual-review-pipeline is a skill published in the GitHub repository ils15/pantheon-legacy (10 stars, last pushed 9d ago), licensed MIT. It adds 32 tokens to every session and 1,825 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 2026-09-03.
Other skills, from other repositories
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
next-dev-loop
Verify Next.js runtime behavior after editing app code. Use this skill to confirm a change actually works in a running app — not just that it compiles or type-checks. Combines /next/mcp (Next.js's view) with agent-browser (the browser's view). Requires a running next dev.
playwright-component-testing
Set up component testing with Playwright using a story gallery — scaffold stories and a gallery dev page driven by the built-in mount fixture, no dedicated component-testing runtime. Use when asked to test React or Vue components in isolation with Playwright, or to migrate off @playwright/experimental-ct-react / -vue.
next-partial-prefetching-optimizer
Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache Components and Partial Prefetching are adopted when the user wants selected URL-specific UI to be instant, wants reusable content to wait for navigation, or needs to choose between default, viewport…