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 skills/akakaui/visual-browser-agent/visual-debuggingnpx skills add Akakaui/visual-browser-agent --skill visual-debugginggit clone --depth 1 https://github.com/Akakaui/visual-browser-agentWhat 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 | $0.00019 | $0.00729 |
| Opus 5 | $0.00010 | $0.00365 |
| Sonnet 5 | $0.00004 | $0.00146 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
visual-debugging 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 yesterday.
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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Debugging Skill
When to Use
Use this skill to debug visual issues:
- Layout breaks (overflow, overlap, misalignment)
- Rendering differences across browsers/viewports
- CSS specificity/conflict issues
- Z-index problems
- Flexbox/Grid layout bugs
- Image loading/aspect ratio issues
- Font rendering problems
- Animation glitches
Instructions
Reproduction
navigateto problematic page/stateinspect_pageto get DOM/CSS contextcapture_screenshotof issue- If intermittent:
record_interactionto capture occurrence
Comparison
For cross-browser/viewport issues:
- Test in each target environment
- Capture same view in each
- Use
review_visual_evidencewith multiple artifacts - Document differences
State Comparison
For before/after or interaction-triggered bugs:
- Capture "before" state
- Trigger interaction
- Capture "after" state
- Compare via vision review
CSS Analysis
From inspect_page accessibility tree + DOM:
- Identify problematic element
- Extract computed styles (via CDP if needed)
- Check: box model, flex/grid properties, positioning, z-index
Console/Network Correlation
- Check console errors during reproduction
- Check network for failed resources (fonts, images, CSS)
- Correlate with visual symptoms
Debugging Workflow
1. Reproduce → capture evidence
2. Isolate → minimal test case
3. Hypothesize → check CSS/DOM
4. Verify → fix attempt → recapture
5. Confirm → document
Output
# Visual Debug Report: {issue}
## Environment
- URL: {url}
- Viewport: {viewport}
- Browser: {browser}
- Steps to reproduce: {steps}
## Evidence
- Before: {screenshot}
- After: {screenshot}
- Recording: {clip}
## Analysis
- Root cause: {CSS/JS/Asset/Environment}
- Affected elements: {selectors}
- Computed styles: {key properties}
## Fix Recommendation
{code snippet or description}
## Verification
- Fixed in: {environments}
- Evidence: {post-fix screenshots}
Safety
- Don't modify page state destructively
- Only capture, don't inject code (unless explicitly allowed)
- Respect private/authenticated pages
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.
- yesterday First seen · 121 lines · 19 tokens per session scan A 307ee8f06552
visual-debugging is a skill published in the GitHub repository Akakaui/visual-browser-agent (0 stars, last pushed 7d ago), licensed MIT. It adds 19 tokens to every session and 729 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.