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 Akakaui/visual-browser-agent --skill visual-regressiongit clone --depth 1 https://github.com/Akakaui/visual-browser-agentWrote 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/akakaui/visual-browser-agent/visual-regression)<a href="https://agentmods.dev/skills/akakaui/visual-browser-agent/visual-regression"><img src="https://agentmods.dev/badge/skills/akakaui/visual-browser-agent/visual-regression/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/akakaui/visual-browser-agent/visual-regression"><img src="https://agentmods.dev/badge/skills/akakaui/visual-browser-agent/visual-regression.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 | $0.00041 | $0.00786 |
| Opus 5.5 | $0.00016 | $0.00314 |
| Sonnet 5.5 | $0.00008 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
visual-regression 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Regression Skill
When to Use
Use this skill to detect unintended visual changes:
- After CSS/style refactors
- After dependency or framework upgrades
- Before releases ("did anything shift?")
- Verifying a fix did not break unrelated screens
- Auditing a route matrix across viewports
Instructions
Baseline Capture
- Define the matrix: routes x viewports (desktop 1280x720, tablet 768x1024, mobile 375x667)
- For each cell:
navigate(route), wait for stability (network idle + fonts loaded),capture_screenshot - Name deterministically:
{route}-{viewport}-baseline; record the action sequence that produced the state (e.g.,["navigate /cart", "click .promo-accordion"]) - Store baselines with route, viewport, timestamp, and action-sequence metadata
Re-run After Changes
- Repeat the exact matrix with identical viewports, wait conditions, and action sequences
- Name candidates with a run ID:
{route}-{viewport}-{runId} - Any drift between runs (viewport size, wait timing, animations mid-flight) invalidates the comparison
Comparing
Two complementary concepts:
- Pixel diff: strict per-pixel inequality; catches everything but is noisy around text antialiasing and subpixel rendering
- Perceptual diff: similarity metrics tolerant of imperceptible rendering variance; fewer false positives on real changes
Pick one strategy per project, set explicit thresholds, and document them next to the baselines.
Reporting Failures
Every reported failure must include:
- Viewport + route
- Full action sequence reproducing the state at capture time
- Side-by-side evidence: baseline, candidate, highlighted diff overlay
- Confidence score plus a judgment on whether the changed region is meaningful (content/layout) or incidental (decoration)
Baseline Management
- Version-control baselines alongside intentional design changes
- Update baselines deliberately, one change at a time - never wholesale re-baselining to make diffs green
- Quarantine flaky regions (ads, timestamps, avatars) with masks or an exclusion list
- Re-baseline after browser or display-scale upgrades, noting it as a run-environment event
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 · 86 lines · 41 tokens per session scan A 0430cb9be928
visual-regression is a skill published in the GitHub repository Akakaui/visual-browser-agent (0 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 786 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.