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 utsavanand/uv-suite --skill uvs-helpgit clone --depth 1 https://github.com/utsavanand/uv-suiteWrote 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/utsavanand/uv-suite/uvs-help)<a href="https://agentmods.dev/skills/utsavanand/uv-suite/uvs-help"><img src="https://agentmods.dev/badge/skills/utsavanand/uv-suite/uvs-help/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/utsavanand/uv-suite/uvs-help"><img src="https://agentmods.dev/badge/skills/utsavanand/uv-suite/uvs-help.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 | $0.00036 | $0.01577 |
| Opus 5.5 | $0.00014 | $0.00631 |
| Sonnet 5.5 | $0.00007 | $0.00315 |
| Haiku 4.5 | $0.00004 | $0.00158 |
Grade A, and why
uvs-help 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 2mo 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.
UV Suite Help
$ARGUMENTS
If the user asked about a specific skill or topic, focus on that. Otherwise, show the full overview below.
Active persona
!grep "Active persona" CLAUDE.md 2>/dev/null || echo "Unknown — check .claude/settings.json"
All available skills
Every skill accepts free-form arguments to direct the agent. Examples shown below.
Understand
| Skill | What it does | Example |
|---|---|---|
/uvs-understand [target] |
Map a codebase or stack (auto-detects scope) | /uvs-understand focus on the auth flow and session management |
Plan
| Skill | What it does | Example |
|---|---|---|
/uvs-spec [requirements] |
Write a technical specification | /uvs-spec webhook retry with exponential backoff, max 3 retries |
/uvs-architect [spec] |
Design architecture, decompose into Acts | /uvs-architect design for horizontal scaling, expect 10x traffic |
Build
| Skill | What it does | Example |
|---|---|---|
/uvs-test [target] |
Generate tests matching project conventions | /uvs-test src/auth/login.ts focus on error paths |
/uvs-test --unit [target] |
Write unit tests | /uvs-test --unit src/auth/login.ts focus on error paths |
/uvs-test --integration [target] |
Write integration tests | /uvs-test --integration the checkout flow end to end |
/uvs-test --eval [prompt] |
Write AI/LLM evaluation cases | /uvs-test --eval test the search ranking prompt for adversarial inputs |
/uvs-prototype [concept] |
Build a static React prototype | /uvs-prototype event booking app with calendar and payment flow |
Review
| Skill | What it does | Example |
|---|---|---|
/uvs-review [focus] |
Code review: correctness, security, perf, slop | /uvs-review pay attention to the new database migration |
/uvs-review --slop [target] |
Detect 6 categories of AI-generated slop | /uvs-review --slop src/components/ check for over-engineering |
/uvs-review --security [target] |
OWASP audit, dependency scan, secret detection | /uvs-review --security src/payments/ focus on webhook signature validation |
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.
- 2mo ago First seen · 137 lines · 36 tokens per session scan A 045b0236ef83
uvs-help is a skill published in the GitHub repository utsavanand/uv-suite (2 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 1,577 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…