Borrowing it
Nothing to install: this file belongs to mtarcure/claude-vibe-squad. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/.agents/skills/visual-verify/SKILL.mdgit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote 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/mtarcure/claude-vibe-squad/visual-verify)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/visual-verify"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/visual-verify/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/mtarcure/claude-vibe-squad/visual-verify"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/visual-verify.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 | $0.00070 | $0.01986 |
| Opus 5 | $0.00035 | $0.00993 |
| Sonnet 5 | $0.00014 | $0.00397 |
| Haiku 4.5 | $0.00007 | $0.00199 |
Grade A, and why
visual-verify 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 9d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Verify
Run the acceptance pass that makes a rendered UI accepted rather than merely built. A UI is not accepted because its tests pass or its code reads correctly — it is accepted when it has been seen (captured and looked at), driven (a real user journey exercised against it), and measured (accessibility and performance scored against declared thresholds).
This is the written-down form of a standard the squad already applies: shared/capabilities/project/web-app.md
and shared/capabilities/project/game-production.md both declare S4 as a required acceptance gate whose
FAIL blocks the S6 ship step. This skill is the procedure for that gate.
When to use
- At S4 Verify in the S0–S7 project lifecycle (
shared/modes/project.md) for any capability whose deliverable renders: web app, game production, or a visual surface inside another card. - A UI change is being handed to review or ship and no one has looked at it.
- A packet asks for "visual verification", screenshots, or a Lighthouse/a11y score.
Skip it — as an explicit, recorded no-op — for backend, CLI, library, and other non-rendering deliverables. Record the skip and its reason; do not silently omit the gate.
Division of labour with visual-regression-baseline
These are not duplicates and must not be merged.
visual-regression-baselineowns the diff: defining the capture set, freezing non-determinism, masking dynamic regions, comparing candidate against baseline under identical recorded conditions, and classifying each delta as intended or regression.- This skill owns the gate: deciding the gate applies, obtaining a reachable target, running the capture / journey / audit passes, invoking the diff skill when a baseline exists, and producing a single accept-or-block verdict for S4.
When a baseline exists, step 4 below hands off to visual-regression-baseline rather than restating it.
Inputs
- A reachable target: a dev-server URL, a local build, or a running app instance. The packet or the S3 build handoff supplies it; this repo has no shared pipeline-state object to read it from, so if the target is absent the gate is blocked, not passed.
- The declared thresholds for the run. Defaults below are a starting point, not a standard — confirm against the packet or the capability card before treating a number as a gate.
- The baseline, if one exists, plus its recorded capture conditions.
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.
- 9d ago First seen · 129 lines · 70 tokens per session scan A 00306ac9d40a
visual-verify is a skill published in the GitHub repository mtarcure/claude-vibe-squad (109 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 1,986 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 2026-08-30.
Other skills, from other repositories
cw-dogfood
Use when a Codewhale change needs proving in the real product, or when asked to build/install/dogfood the local binaries: stamped release build, atomic install, fresh-shell verification, and the manual QA that gates cannot cover.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
issue-to-pr
Implement one bounded repository issue with normal host tools, prove the tested change through one scafld finalize wall, and optionally publish the exact pull request through scoped provider authority with readback.