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 wsauret/flywheel --skill vscode-uatgit clone --depth 1 https://github.com/wsauret/flywheelWrote 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/wsauret/flywheel/vscode-uat)<a href="https://agentmods.dev/skills/wsauret/flywheel/vscode-uat"><img src="https://agentmods.dev/badge/skills/wsauret/flywheel/vscode-uat/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/wsauret/flywheel/vscode-uat"><img src="https://agentmods.dev/badge/skills/wsauret/flywheel/vscode-uat.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 | $0.00016 | $0.00379 |
| Opus 5.5 | $0.00006 | $0.00152 |
| Sonnet 5.5 | $0.00003 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
vscode-uat 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 4d 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.
What it actually says
VS Code UAT
Input: extension acceptance criteria, source revision, the universal package, and a session scratch directory.
Compose generic UAT. Build the required VSIX. Allocate unique profile, extension, workspace, log, screenshot, marker, and dynamically selected CDP-port resources under the supplied scratch directory. Never use a fixed /tmp path, shared port, or personal editor profile. Launch only the isolated instance, install the exact VSIX, and prove reload with a fresh marker. Connect through CDP after bounded readiness. Rediscover element references after navigation or reload. Exercise each criterion through packaged extension UI, capture screenshots and extension-host or webview diagnostics, and prove recovery for one load-bearing failure path. Close only the isolated instance and clean owned resources.
Launch the editor binary directly with --user-data-dir, --extensions-dir, and --remote-debugging-port; the code command and open -a reuse the person's own instance. Keep the isolated HOME short, because a unix socket path over 104 bytes fails the extension's runtime connection on macOS. A DevTools endpoint that never answers and a refused screen capture leave the render unobserved: bun run --cwd vscode e2e then proves the stack, not the appearance, and the report says so. Client behaviour that does not depend on the editor host is proven with webview-uat first.
Stop when every criterion has a generic UAT status or the editor cannot be driven safely. Return VSIX identity, isolated-instance details, interactions, screenshots and logs, criterion statuses, recovery evidence, and cleanup state. Package, launcher, port, CDP, CSP, or extension-host failure returns blocked with diagnostics.
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.
- 4d ago First seen · 15 lines · 16 tokens per session scan A a945d7659c3a
vscode-uat is a skill published in the GitHub repository wsauret/flywheel (19 stars, last pushed yesterday), licensed Apache-2.0. It adds 16 tokens to every session and 379 once invoked, about $0.0001 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 2026-11-03.
vscode-uat compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vscode-uatwsauret/flywheel | Skill | 19 | yesterday | Apache-2.0 | A | 16 | Claude Code, Codex |
| webapp-testingHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 32 | Claude Code, Codex |
| verifyHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 25 | Claude Code, Codex |
| computer-useHmbown/Codewhale | Skill | 41k | 1mo ago | MIT | A | 59 | Claude Code, Codex |
| test-browsergvkhosla/compound-engineering-pi | Skill | 52 | 1mo ago | MIT | A | 14 | Claude Code |
| playwright-browserlfyxhappy/lfcode | Skill | 2 | 1mo ago | MIT | A | 42 | Claude Code, Codex |
| e2e-test-engineerlfyxhappy/lfcode | Skill | 2 | 1mo ago | MIT | A | 62 | Claude Code, Codex |