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 daeryundf2-prog/LAZYANTIGRAVITY --skill visual-qagit clone --depth 1 https://github.com/daeryundf2-prog/LAZYANTIGRAVITYWrote 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/daeryundf2-prog/lazyantigravity/visual-qa)<a href="https://agentmods.dev/skills/daeryundf2-prog/lazyantigravity/visual-qa"><img src="https://agentmods.dev/badge/skills/daeryundf2-prog/lazyantigravity/visual-qa/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/daeryundf2-prog/lazyantigravity/visual-qa"><img src="https://agentmods.dev/badge/skills/daeryundf2-prog/lazyantigravity/visual-qa.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 | $0.00212 | $0.03734 |
| Opus 5.5 | $0.00085 | $0.01494 |
| Sonnet 5.5 | $0.00042 | $0.00747 |
| Haiku 4.5 | $0.00021 | $0.00373 |
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 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Antigravity Tool Mapping (default)
This plugin defaults to Google Antigravity. Read ../references/antigravity-tools.md.
| Intent | Antigravity action |
|---|---|
| Explore / research / plan / implement / QA / review | invoke_subagent + TASK/DELIVERABLE/SCOPE/VERIFY + role envelope |
| Wait / poll children | Stay in parent; re-invoke incomplete lanes |
| Child model hint | Pass Subagents[].Model: flash (plan/code/research), pro (verify), flash_lite (tiny chores), inherit |
Use Antigravity tools only (invoke_subagent). Do not invent foreign spawn/wait/goal APIs or OpenCode kwargs.
Purpose and when to use
- Use after you build or change any UI, before calling it done. Covers web/page UIs and TUI/terminal UIs.
- Use when output must match a mock, a baseline, or a stated design intent; when you suspect a regression; when CJK (Korean/Japanese/Chinese) text may clip or misalign; when a claimed design system might actually be a flat image; when a terminal layout may overflow or its borders may break.
- Skip when there is no rendered surface (pure backend or library logic with no visual or terminal output). For broad post-implementation review use review-work; this skill is the visual specialist.
In the commands below, $SKILL_DIR is this skill's own directory (the folder containing this SKILL.md). The bundled script lives at scripts/cli.ts inside it.
Step 1 - Detect the surface
- Web/page UI: renders in a browser (HTML/CSS/JS, components, canvas, SVG). Evidence is screenshots.
- TUI/terminal UI: renders as text in a terminal (box-drawing, panes, status lines, REPL/TUI apps). Evidence is terminal captures.
If the change touches both, run both capture tracks and feed both into the passes.
Empirical Vision & OCR Rules (Anti-Hallucination & Quota Independence)
- Mandatory Absolute Paths: Never pass vague or relative filenames (e.g.
slide-01.png) when dispatching visual reviews. Without absolute paths (file:///absolute/path/to/img.png), models risk hallucinating plausible-sounding contents that do not exist. - Verbatim Title / Label Quote Proof: Always instruct the reviewer: "Quote the exact title and main UI labels verbatim from the image." Mismatched quotes prove the image was not genuinely inspected.
- Quota Independence: Vision / OCR inspections consume the text token bucket, NOT the image generation capacity bucket (
gemini-3.1-flash-image). Even if image generation encounters a 429 limit, visual QA loops continue to function at full capacity.
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/frontend-ui-ux.md 5.0 KB
- references/ui-loopback.md 3.9 KB
- scripts/ansi.test.ts 1.0 KB runs code
- scripts/ansi.ts 499 B runs code
- scripts/cli.test.ts 2.5 KB runs code
- scripts/cli.ts 2.4 KB runs code
- scripts/east-asian-width.test.ts 1.8 KB runs code
- scripts/east-asian-width.ts 3.0 KB runs code
- scripts/image-diff.test.ts 2.5 KB runs code
- scripts/image-diff.ts 3.7 KB runs code
- scripts/png-crc.ts 682 B runs code
- scripts/png-decode.test.ts 1.4 KB runs code
- scripts/png-decode.ts 5.1 KB runs code
- scripts/png-synth.ts 1.6 KB runs code
- scripts/tui-grid.test.ts 1.9 KB runs code
- scripts/tui-grid.ts 2.6 KB runs code
- scripts/types.ts 1.3 KB runs code
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 b4ff14a5b109
- 1mo ago First seen · 297 lines · 212 tokens per session scan A 52cbfc8de004
visual-qa is a skill published in the GitHub repository daeryundf2-prog/LAZYANTIGRAVITY (14 stars, last pushed 7d ago), licensed MIT. It adds 212 tokens to every session and 3,734 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
typescript-specifications
Structural verification for TypeScript and JavaScript — tsc --noEmit, linter (eslint/biome). Load when planning, implementing, or reviewing TypeScript/JavaScript code (.ts, .tsx, .js, .jsx; tsconfig.json, package.json).
vitest
Vitest fast unit testing framework powered by Vite with Jest-compatible API.
validate-type-safety
Run the full 5-step TypeScript validation gate: type check, reward hacking scan, test inclusion, tests, and lint. This skill provides a structured multi-step pipeline that you cannot replicate on your own — it detects the project's package manager and linter automatically, checks tsconfig strictness, and invokes…
V3 Core Implementation
Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing.
tdd
Build this test-first, one behavior at a time: $ARGUMENTS.
om-troubleshooter
Diagnose and fix standalone Open Mercato bugs across scope, commands, locking, fields, generated registries, UI hydration, cache/search, bootstraps, queues, and providers. Use for "fix bug", "why does this fail", "regression", "debug", "napraw błąd", or a failing test.