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/utsavanand/uv-suite/uvs-commitnpx skills add utsavanand/uv-suite --skill uvs-commitgit clone --depth 1 https://github.com/utsavanand/uv-suiteWhat 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 | $0.00039 | $0.00721 |
| Opus 5 | $0.00019 | $0.00360 |
| Sonnet 5 | $0.00008 | $0.00144 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
uvs-commit 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 yesterday.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent
$ARGUMENTS
Current state
!git status --short 2>/dev/null | head -30 || echo "not a git repo"
!git diff --cached --stat 2>/dev/null || echo "nothing staged"
!git diff --stat 2>/dev/null || echo "no unstaged changes"
Pipeline — run these steps in order
1. Run tests
Find and run the project's test command. If tests fail, fix the failures before continuing. If they can't be fixed in 2 attempts, stop and report.
2. Run lint
If a lint command exists (npm run lint, ruff check, etc.), run it. Fix auto-fixable issues.
3. Quick slop check
Scan changed files for the most obvious patterns:
toBeTruthy()/toBeDefined()in test files- Bare
except: passin Python
Don't run the full /uvs-review --slop agent — just grep for mechanical patterns.
4. Review the diff
Read the full diff. Check for:
- Correctness: does it do what it should?
- Security: any obvious issues? (hardcoded secrets, missing auth checks)
- Completeness: anything half-done or TODO'd?
If you find issues, fix them. If they need human input, stop and ask.
5. Stage and commit
- Stage the relevant files (not
.env, notnode_modules, not build artifacts) - Write a commit message. If the user provided one in $ARGUMENTS, use it. Otherwise, write a concise message that describes the WHY, not the WHAT.
- Commit.
6. Open PR (if requested)
If the user said "pr" in their arguments, or if on a feature branch:
- Push the branch
- Open a PR with
gh pr create - Title: short, under 70 chars
- Body: summary bullets + test plan
7. Checkpoint
After committing, write a checkpoint to latest.md in this session's checkpoint
directory (shown below) with what was committed:
!"${CLAUDE_PROJECT_DIR:-.}"/.claude/hooks/checkpoint-helper.sh dir
Danger zones
!cat DANGER-ZONES.md 2>/dev/null || echo "No DANGER-ZONES.md"
Rules
- If tests fail and can't be fixed quickly, STOP. Don't commit broken code.
- If the diff touches a danger zone file, flag it before committing.
- Prefer separate commits per logical change if there are unrelated changes staged.
- Never commit .env, credentials, or secrets.
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.
- yesterday First seen · 95 lines · 39 tokens per session scan A 741498a265eb
uvs-commit is a skill published in the GitHub repository utsavanand/uv-suite (2 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 721 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…