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 synaptiai/synapti-marketplace --skill visual-verificationgit clone --depth 1 https://github.com/synaptiai/synapti-marketplaceWrote 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/synaptiai/synapti-marketplace/visual-verification)<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/visual-verification"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/visual-verification/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/synaptiai/synapti-marketplace/visual-verification"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/visual-verification.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 | $0.00137 | $0.01309 |
| Opus 5.5 | $0.00055 | $0.00524 |
| Sonnet 5.5 | $0.00027 | $0.00262 |
| Haiku 4.5 | $0.00014 | $0.00131 |
Grade A, and why
visual-verification scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Verification
Contract
Iron law: UI changes are visually verified or explicitly skipped with a structured result — a
passing build does not prove the page renders, and a screenshot does not prove an interaction
works. Invoked with runtime-verification by /flow:start Phase 4 (retried at step 8) and
/flow:pr Phase 4 via Agent(integration-verifier) when the diff has UI files or criteria
mention UI. Returns the Visual Verification and Visual Evidence tables, one
Viewport/Screenshot/Result/Observed: block per viewport for ### Visual analysis, a
Step:-carrying block per step on an interaction criterion, and P1/P2/P3 findings
(category=visual), labeled PASS/FAIL/SKIP/SKIP_WARN/SKIP_USER_APPROVED/MANUAL/BLOCKED.
Permitted skips: SKIP when no UI signal fires or the dev server is unavailable; SKIP_WARN,
SKIP_USER_APPROVED, MANUAL only via the cascade.
UI Relevance
Activates when changed files match \.(tsx|jsx|vue|html|css|scss|svelte)$, or criteria contain
UI, page, display, render, visual, layout, responsive, component or style. Neither: SKIP — no UI-relevant changes detected. requireVisualVerification (default false) controls escalation only; an unattempted
UI change still yields SKIP_WARN.
Browser Tool Cascade
Only an interactive tool can run a flow: a picture-only tool cannot click, and treating it as
if it could reports a flow that performed none. Playwright MCP and Chrome DevTools MCP are
interactive; the npx playwright screenshot CLI and compound-engineering browser skills are
not.
Playwright MCP exposes browser_navigate, browser_snapshot, browser_click, browser_type,
browser_take_screenshot, browser_console_messages. Take names from the server's docs, not
memory: a call to a tool that does not exist finds nothing and says nothing, so the check never
runs and nothing reports it.
No tool: SKIP_WARN, or BLOCKED when requireVisualVerification is true (escalate per
references/escalation-format.md). Never install silently.
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 Changed · +7 lines 48dab6f1ea2c
- 1mo ago Changed ccfe546a4791
- 1mo ago Changed · -110 lines 5a98dda744d5
- 1mo ago First seen · 205 lines · 137 tokens per session scan A 58e2bc8a911f
visual-verification is a skill published in the GitHub repository synaptiai/synapti-marketplace (7 stars, last pushed 9d ago), licensed Apache-2.0. It adds 137 tokens to every session and 1,309 once invoked, about $0.0005 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 skills, from other repositories
ios-testing-patterns
XCTest and XCUITest execution workflows and flaky test detection patterns.
ui-automation-workflows
Accessibility-first UI automation using IDB. Query accessibility tree (fast, 50 tokens) before screenshots (slow, 170 tokens). Use when automating simulator interactions, tapping UI elements, finding buttons, or testing user flows. Covers idb-ui-describe, idb-ui-tap, idb-ui-find-element patterns.
wicked-garden-qe-a11y-test-engineer
Accessibility specialist — axe-core + pa11y, WCAG 2.1 AA / 2.2 AA, keyboard-only flows, focus-ring detection, prefers-reduced-motion, color contrast ≥ 4.5:1. Writes axe/pa11y JSON to the evidence dir, appends a verdict row to DomainStore, and defaults to a CONDITIONAL verdict because automated tools only catch 30% of…
visual-diff
Visual Regression Testing — screenshot comparison before and after changes. Use when user wants to check for visual regressions, compare UI changes, or verify CSS/layout changes didn't break anything.
triaging-visual-review-runs
Inspects PostHog Visual Review (VR) runs that gate PR merges with screenshot regression checks. Use when the user mentions "visual review", "VR", "snapshot diff", "screenshot test", "storybook regression", "playwright snapshot", "quarantine", asks why a PR is blocked or what changed visually, wants to triage the VR…
e2e-tests
Generate automated API/E2E tests for features that already exist — brownfield code, features shipped before the eval net, or manual test-plan scenarios worth automating. Use when the user says "generate e2e tests", "backfill tests", "automate the test plan", or "qa tests for {feature}".