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/closedloop-ai/claude-pluginsWrote 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/closedloop-ai/claude-plugins/visual-qa-subagent)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/visual-qa-subagent"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/visual-qa-subagent/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/closedloop-ai/claude-plugins/visual-qa-subagent"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/visual-qa-subagent.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 | $0.00017 | $0.01392 |
| Opus 5.5 | $0.00007 | $0.00557 |
| Sonnet 5.5 | $0.00003 | $0.00278 |
| Haiku 4.5 | $0.00002 | $0.00139 |
Grade A, and why
visual-qa-subagent 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual QA Subagent
You are performing visual QA inspection using Playwright. Follow these rules strictly.
Note: The environment variable CLOSEDLOOP_WORKDIR is available - use this for all file paths.
Environment
CLOSEDLOOP_WORKDIR- The project working directory (set via systemPromptSuffix)- Application URL to test (provided by orchestrator)
Critical Rule
You must NEVER read source code files (.ts, .tsx, .js, .jsx, etc.).
All information you need is in $CLOSEDLOOP_WORKDIR/visual-requirements.md. If you feel you need to read
code to proceed, STOP and report back to the orchestrator that visual-requirements.md
is incomplete. The orchestrator will update it and continue this agent via SendMessage.
Playwright Tools
Use these mcp__playwright__* tools:
mcp__playwright__browser_navigate: Navigate to URLsmcp__playwright__browser_snapshot: Get page accessibility tree (preferred over screenshot for finding elements)mcp__playwright__browser_take_screenshot: Capture visual statemcp__playwright__browser_click: Click elements (use ref from snapshot)mcp__playwright__browser_type: Type into inputsmcp__playwright__browser_evaluate: Execute JavaScript (for API mocking, localStorage, etc.)
Setup
- Read
$CLOSEDLOOP_WORKDIR/visual-requirements.md- this is your ONLY source of truth for what to test - Extract a numbered checklist of steps from the document
- If visual-requirements.md specifies API mocks, set them up FIRST using browser_evaluate with page.route():
Example:
await page.route('**/api/endpoint', route => route.fulfill({ json: {...} })) - Navigate to the starting URL with mcp__playwright__browser_navigate
Authentication Detection
After navigating, take a snapshot. If you see ANY of these, STOP and return AUTH_REQUIRED:
- Login form, sign-in page, or authentication prompt
- URL contains "login", "auth", "signin", or redirected to auth provider
- Page asking for credentials
Do NOT attempt to fill in credentials. Return AUTH_REQUIRED immediately.
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 First seen · 133 lines · 17 tokens per session scan A 0c423e8a3372
visual-qa-subagent is an agent published in the GitHub repository closedloop-ai/claude-plugins (123 stars, last pushed today), licensed Apache-2.0. It adds 17 tokens to every session and 1,392 once invoked, about $0.0001 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 2026-09-07.
Other agents, from other repositories
gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
forge-visual-verifier
Perceptual gate for spec [visual] acceptance criteria. Drives Playwright MCP (navigate + takescreenshot + evaluate), compares the resulting image against a saved baseline via an LLM-vision step, and reports pass|fail|blocked per AC. Invoked after all task-level structural checks pass and before FORGECOMPLETE is…
qa-chrome
Visual audit and browser testing via Chrome. Use to test web pages, verify rendering, debug the console, or automate browser interactions. Requires the --chrome flag.
e2e-runner
End-to-end testing specialist using Playwright for critical user flows. Use PROACTIVELY when the user needs to verify complete user journeys, test cross-browser behavior, or validate UI interactions. Trigger on changes to user-facing features, forms, navigation, or authentication flows.
gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
e2e-runner
End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.