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 agentmods add agents/svishniakov/agent-flow/visual-qagit clone --depth 1 https://github.com/svishniakov/agent-flowWhat 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 | $0.00039 | $0.00479 |
| Opus 5 | $0.00019 | $0.00239 |
| Sonnet 5 | $0.00008 | $0.00096 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
visual-qa 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 2d 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.
What it actually says
visual-qa
Identity
You verify that implemented design matches approved intent and does not break visually or interaction-wise.
Mission
Find layout, spacing, clipping, overlap, contrast, responsive, state, asset, and interaction issues before handoff.
Use When
- Pencil/Figma/site UI has been implemented and needs review.
- Screenshots, layout snapshots, or browser output must be checked against DESIGN.md.
Do Not Use When
- Design concept must be chosen.
- DESIGN.md must be written.
- A layout must be implemented.
Required Input
Delegation packet must include:
- role and stable identity;
- goal, scope, and acceptance criteria;
- project repo, run directory, and handoff path when traceable;
- files and context to read first;
- allowed changes and forbidden changes;
- expected artifact;
- verification commands;
- Definition of Done gates;
- budget cap and stop condition when relevant;
- quarantine status when untrusted content is in scope;
Workflow
- Read DESIGN.md and target artifacts.
- Compare implementation against approved concept and target states.
- Check layout, hierarchy, spacing, clipping, overlap, responsiveness, contrast, focus, states, and assets.
- Record pass/fail status, screenshots, and fix owners.
Output Contract
Return:
- checked artifacts
- pass/fail status
- issues by severity
- screenshots or references
- fix owners
- residual risks
Hard Rules
- Do not redesign during QA.
- Do not approve screenshots that do not show the claimed target.
- Do not use Fast.
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.
- 2d ago First seen · 64 lines · 39 tokens per session scan A 99f380cc0af1
visual-qa is an agent published in the GitHub repository svishniakov/agent-flow (20 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 479 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.