Borrowing it
Nothing to install: this file belongs to vscarpenter/gsd-task-manager. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vscarpenter/gsd-task-manager/main/.agents/skills/verify-frontend-change/SKILL.mdgit clone --depth 1 https://github.com/vscarpenter/gsd-task-managerWrote 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/vscarpenter/gsd-task-manager/verify-frontend-change)<a href="https://agentmods.dev/skills/vscarpenter/gsd-task-manager/verify-frontend-change"><img src="https://agentmods.dev/badge/skills/vscarpenter/gsd-task-manager/verify-frontend-change/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/vscarpenter/gsd-task-manager/verify-frontend-change"><img src="https://agentmods.dev/badge/skills/vscarpenter/gsd-task-manager/verify-frontend-change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.02645 |
| Opus 5 | $0.00000 | $0.01323 |
| Sonnet 5 | $0.00000 | $0.00529 |
| Haiku 4.5 | $0.00000 | $0.00265 |
Grade A, and why
verify-frontend-change 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 9d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
verify-frontend-change
Confirm a frontend change does what it's supposed to in the running app, not just in your head. The output is a PASS/FAIL verdict backed by evidence — never a confident guess.
This skill exists because two traps in this codebase silently turn verification into theater:
- The service worker serves stale JS chunks. You edit
border-l-4→border, reload, and still see the old UI. Your screenshot "confirms" code that isn't running. - Data surfaces render empty on a fresh load. The dashboard and matrix have nothing to show until tasks exist. A screenshot of an empty dashboard "confirms" a layout you never actually saw.
Either trap produces a false PASS — the most dangerous outcome, because it ends the investigation with the wrong answer. Everything below is built to make PASS mean something.
Right-size the effort. The verification is the observation of the running change — the rendered result, the click working, the console staying clean. Static checks (typecheck, the unit suite) are a cheap precondition, not the verification, and they don't need to balloon: run the few that bear on this change, not the whole app. A CSS spacing tweak doesn't warrant the full test suite or a fresh Playwright run; it warrants eyes on the rendered card. Spending twenty minutes on static analysis to avoid two minutes of looking is the over-engineering this skill is meant to replace.
When to use
Use this after editing any .tsx/.jsx under components/ or app/, or any change that affects what the user sees or does — the matrix, capture bar, edit drawer, dashboard, settings, task cards. Reach for it before pushing or opening a PR on UI work.
Don't use it for backend/sync-only logic (lib/sync/**), pure data transforms with unit-test coverage, or styling-only token tweaks already covered by inkwell-retrofit — those have better-fit verification.
Default dimensions
Verify these two by default — they catch the most regressions per unit of effort:
What ships with it
3 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.
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.
- 9d ago First seen · 137 lines · 0 tokens per session scan A 5e7de009944e
verify-frontend-change is a skill published in the GitHub repository vscarpenter/gsd-task-manager (25 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,645 tokens. 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
lastest
Lastest is a visual regression testing platform. It records browser tests, runs them via Playwright, diffs screenshots, and uses AI to classify changes. Available as an MCP server for AI agent integration.
quality-engineering-selector-stability
Cross-stack selector and test-id policy for web and mobile automation. Use when writing or reviewing E2E/UI test locators, or adding data-testid/accessibility identifiers to components.
ui-aqa-flow
Workflow for automated QA: integration and end-to-end UI test automation, page objects, etc.
browser-inspection-workflow
Coordinate rendered behavior and state evidence.
visual-regression-lab
Compare captures; stitch lazy/animated pages.
cross-browser-qa
Verify browser-engine compatibility.