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 ericfitz/skills --skill vrtgit clone --depth 1 https://github.com/ericfitz/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/ericfitz/skills/vrt)<a href="https://agentmods.dev/skills/ericfitz/skills/vrt"><img src="https://agentmods.dev/badge/skills/ericfitz/skills/vrt/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/ericfitz/skills/vrt"><img src="https://agentmods.dev/badge/skills/ericfitz/skills/vrt.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 | $0.00051 | $0.01088 |
| Opus 5.5 | $0.00020 | $0.00435 |
| Sonnet 5.5 | $0.00010 | $0.00218 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
vrt 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Regression Triage
When a Playwright visual regression test fails, present the baseline, actual, and diff images alongside the user's current task context, then guide the user to either fix the underlying bug or update the baseline.
Configuration (optional)
Reads .local/repos.json (walked up from pwd) to look up the GitHub owner/repo for the current project so that gh issue view can fetch task context. If .local/repos.json is missing or the current project isn't found, the skill falls back to whatever gh is configured to use.
{
"<name>": {
"path": "<absolute repo path matching pwd>",
"github": {"owner": "...", "repo": "..."}
}
}
The skill identifies the current project by matching pwd (or its parent) to an entry's path value; the matching entry's key is <name>.
A skill-specific config file .claude/visual-regression.config.json is supported but optional:
{
"test_command": "pnpm test:e2e --project=visual-regression",
"update_command": "pnpm test:e2e --project=visual-regression --update-snapshots",
"results_glob": "test-results/**/*-actual.png",
"snapshot_naming": {
"actual_suffix": "-actual.png",
"expected_suffix": "-expected.png",
"diff_suffix": "-diff.png"
}
}
If the config is missing, defaults match Playwright's standard layout and use a generic npx playwright test invocation.
Process
1. Gather task context
Before examining images, understand what the user is working on:
git branch --show-current— current branch.git log --oneline -5— recent commits; look for issue numbers and Conventional Commit types.- If commits or branch name reference an issue number
#N, look up the issue:
IfOWNER=$(jq -r --arg n "$NAME" '.[$n].github.owner // empty' .local/repos.json) # $NAME = matched key REPO=$(jq -r --arg n "$NAME" '.[$n].github.repo // empty' .local/repos.json) gh issue view "$N" --repo "$OWNER/$REPO" --json title,bodyOWNER/REPOare unavailable, rungh issue view "$N"with no--repoflag. git diff --name-only HEAD~5— recently changed files.
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 · 108 lines · 51 tokens per session scan A fdede1a04258
vrt is a skill published in the GitHub repository ericfitz/skills (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 1,088 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 2026-09-04.
Other skills, from other repositories
a11y-ally
Use when running comprehensive WCAG accessibility audits with axe-core + pa11y + Lighthouse, generating context-aware remediation, or testing video accessibility. Supports 3-tier browser cascade with graceful degradation.
accessibility-testing
WCAG 2.2 compliance testing, screen reader validation, and inclusive design verification. Use when ensuring legal compliance (ADA, Section 508), testing for disabilities, or building accessible applications for 1 billion disabled users globally.
image-compare
Compare two image files on disk and report what changed, region by region. Trigger on "what changed between these two images", "diff these PNGs", "did this render drift", "compare screenshots/exports/renders".
frontend-manual-testing
Use when the task changes anything a user sees in a web app - booting it, driving flows with the browser tools, the four-width check, console/network/keyboard checks and the visual checklist.
playwright-scanner
Internal helper: behavioral scans via Playwright for keyboard and state.
visual-qa-testing
Visually QA a web application by launching it in Cursor's built-in browser, taking screenshots, checking console errors, and auditing network requests. Use after making UI changes to verify they look correct.