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/fiveonecode/agent-skills/hint-overlay-visual-verificationnpx skills add fiveonecode/agent-skills --skill hint-overlay-visual-verificationgit clone --depth 1 https://github.com/fiveonecode/agent-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/fiveonecode/agent-skills/hint-overlay-visual-verification)<a href="https://agentmods.dev/skills/fiveonecode/agent-skills/hint-overlay-visual-verification"><img src="https://agentmods.dev/badge/skills/fiveonecode/agent-skills/hint-overlay-visual-verification.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 | $0.00063 | $0.02070 |
| Opus 5 | $0.00032 | $0.01035 |
| Sonnet 5 | $0.00013 | $0.00414 |
| Haiku 4.5 | $0.00006 | $0.00207 |
Grade A, and why
hint-overlay-visual-verification 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 3d 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hint Overlay Visual Verification
Scope
Use this skill only when screenshot evidence is meant to approve an in-app hint overlay, coach mark, spotlight, or anchored instructional callout.
This is a visual verification contract. It does not capture screenshots, drive the interface, measure accessibility values, or create marketing artwork. Use the available image, browser, or computer inspection capability to perform the checks below.
Do not use this skill for:
- generic screenshot or broad UI review;
- App Store screenshot capture, resizing, framing, composition, or upload;
- reference-poster or marketing-composite approval;
- proving interaction behavior from a still image alone.
If a hard gate fails or required evidence is missing, report NOT VERIFIED.
Required Inputs
Approval requires all of the following to be explicit:
- App, route, page, or surface under review.
- Scenario and overlay state.
- Target element and expected highlight bounds or anchor.
- Required callout text and required visible controls.
- Elements that must be hidden or de-emphasized.
- Required device, viewport, operating-system, and light/dark coverage.
- Expected pointer, tail, dismissal, and tap behavior.
- Screenshot paths and capture labels.
- Build, deployment, or page-version evidence when freshness matters.
- Separate interaction evidence when approval includes tap or dismissal behavior.
If an input is unavailable, continue only far enough to report the missing evidence. Do not infer approval from a plausible-looking screenshot.
Evidence Limits
- Inspect the original image at the highest available detail before judging small text, pointer tips, aperture edges, or safe-area clearance.
- A still image can show a rendered state. It cannot prove that a target is tappable, a callout ignores taps, an outside tap dismisses, or an animation remains correct over time.
- A screenshot cannot prove that it came from the latest build without independent capture or build evidence.
- Visual inspection can identify likely contrast problems but is not a measured WCAG conformance test. Measure when exact conformance is required.
- When image detail or capture provenance is insufficient, fail closed and name the missing evidence.
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.
- 3d ago First seen · 243 lines · 63 tokens per session scan A 861c274b5c37
hint-overlay-visual-verification is a skill published in the GitHub repository fiveonecode/agent-skills (19 stars, last pushed 12d ago), licensed MIT. It adds 63 tokens to every session and 2,070 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…