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/mlopscommunity/coding-agents-conference-skills/visual-regressionnpx skills add mlopscommunity/Coding-Agents-Conference-skills --skill visual-regressiongit clone --depth 1 https://github.com/mlopscommunity/Coding-Agents-Conference-skillsWrote 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/mlopscommunity/coding-agents-conference-skills/visual-regression)<a href="https://agentmods.dev/skills/mlopscommunity/coding-agents-conference-skills/visual-regression"><img src="https://agentmods.dev/badge/skills/mlopscommunity/coding-agents-conference-skills/visual-regression.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.02079 |
| Opus 5 | $0.00020 | $0.01040 |
| Sonnet 5 | $0.00008 | $0.00416 |
| Haiku 4.5 | $0.00004 | $0.00208 |
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 6d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Regression Testing
Overview
Two-mode skill for catching visual regressions. During development, create screenshot walkthroughs of affected flows. At release time, compare screenshots between two git refs and use a sub-agent to classify changes as expected or unexpected.
Core principle: Screenshots are cheap and regenerable. Never commit them to git. The value is in the comparison and classification, not the screenshots themselves.
Dependency: Playwright must be installed in the project.
When to Use
- After making any user-facing change (component, layout, CSS, copy)
- Before a release to catch accumulated visual regressions
- When QA is a bottleneck and you need to prioritize what humans review
When NOT to Use
- API-only or backend-only changes
- As a CI gate on PRs (too slow — run at release time only)
Common Mistakes
| Mistake | Why it's wrong |
|---|---|
| Committing screenshots to git | They're regenerable. Bloats repo for no value. |
| Running visual comparison in CI on every PR | Too slow. Rob: "You cannot do this in PR merge." |
| Using hard-coded pixel thresholds alone | The key insight is AI-powered analysis of why something changed, not just that it changed. |
| Over-engineering with versioned baselines and symlinks | Keep it simple: checkout old tag, screenshot, checkout new tag, screenshot, diff. |
| Skipping the textual walkthrough | Screenshots without descriptions are useless for review. Always include what the user sees and what flow this belongs to. |
Mode 1: document (During Development)
When you make a user-facing change, do this:
Step 1: Identify affected flows
Look at what you changed and list the user flows it touches (e.g., "login flow", "checkout step 2").
Step 2: Write or update Playwright screenshot scripts
Create scripts under e2e/visual/ that walk through each affected flow and capture screenshots at each meaningful step.
// e2e/visual/login-flow.spec.ts
import { test } from '@playwright/test';
test('login flow walkthrough', async ({ page }) => {
// Step 1: Landing page
await page.goto('/');
await page.waitForLoadState('networkidle');
await page.screenshot({ path: '.screenshots/flows/login-flow/01-landing-page.png', fullPage: true });
// Step 2: Click login, see form
await page.click('[data-testid="login-button"]');
await page.waitForSelector('[data-testid="login-form"]');
await page.screenshot({ path: '.screenshots/flows/login-flow/02-login-form.png', fullPage: true });
// Step 3: Fill and submit
await page.fill('[name="email"]', '[email protected]');
await page.fill('[name="password"]', 'password123');
await page.click('[data-testid="submit"]');
await page.waitForSelector('[data-testid="dashboard"]');
await page.screenshot({ path: '.screenshots/flows/login-flow/03-dashboard.png', fullPage: true });
});
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.
- 6d ago First seen · 231 lines · 40 tokens per session scan A 640e81cadfee
visual-regression is a skill published in the GitHub repository mlopscommunity/Coding-Agents-Conference-skills (37 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 2,079 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 skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
run-integration-tests
Build, pack, and run .NET MAUI integration tests locally. Validates templates, samples, and end-to-end scenarios using the local workload.
cli-e2e-testcase-writer
Use when adding or updating Go CLI E2E coverage for one tests/clie2e/{domain} domain of the compiled lark-cli, especially when the work requires live --help or schema exploration, scenario-based clie2e.RunCmd workflows, and per-domain coverage.md maintenance.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
__SKILL_ID__
This fixture verifies that skill content can be written into the target sandbox and queried back immediately.
agent-device-evidence
Records iOS/Android native MP4 evidence for test/repro flows extracted from an Expensify GitHub PR or issue. Use when the user asks to "record the flow for PR.