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.
git clone --depth 1 https://github.com/smicolon/ai-kitWrote 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/commands/smicolon/ai-kit/review-perf)<a href="https://agentmods.dev/commands/smicolon/ai-kit/review-perf"><img src="https://agentmods.dev/badge/commands/smicolon/ai-kit/review-perf.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 5.1 | $0.00043 | $0.01929 |
| Opus 5 | $0.00022 | $0.00964 |
| Sonnet 5 | $0.00009 | $0.00386 |
| Haiku 4.5 | $0.00004 | $0.00193 |
Grade A, and why
review-perf 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are reviewing the current branch for performance and rendering efficiency ONLY. Ignore visual polish and accessibility. Overlap with /review-arch is fine for issues with direct performance consequences, but don't re-raise pure architecture nits.
Step 0 — Interpret the scope and detect the data-fetching library
User argument: $ARGUMENTS
Classify into one of four modes. Check package.json for the data-fetching library (TanStack Query, SWR, Apollo, or native fetch). The first two lines of your output MUST be:
Mode: <whole-branch | path: <p> | feature: <name> | base: <branch>> | Data fetcher: <tanstack-query | swr | apollo | native-fetch | none>
Reviewed N files in scope. Found X P0, Y P1, Z P2 findings.
- Mode A — Whole branch (empty): Review everything changed vs
main. - Mode B — Path scope (contains
/or a known extension, or matchesgit ls-files $ARGUMENTS): Review only changes inside that path. - Mode C — Feature scope (single bareword): Find files related via
git ls-files | grep -i <feature>, intersect with branch diff. - Mode D — Base branch (matches a real branch): Review against that base instead of
main.
Ambiguous → prefer branch if git branch -a confirms.
Step 1 — Scope the diff
Based on the mode:
- A:
git diff main...HEAD --stat - B:
git diff main...HEAD --stat -- <path> - C: Compute the file list from the feature match, diff each relevant file.
- D:
git diff <base>...HEAD --stat
List modified components, hooks, and any package.json / lockfile / config changes (those affect bundle size).
Step 2 — Evaluate each changed file
Rendering efficiency
- Unnecessary re-renders — inline object/array/function props passed to memoized children? New reference on every render?
- Memoization correctness —
React.memo,useMemo,useCallbackused where it actually helps (stable props to expensive children, expensive computation), or cargo-culted where it's dead weight? - Derived state — stored in
useState+ synced viauseEffectinstead of computed during render? - Effects — running too often? Missing dependencies? Doing work that should be event-driven?
- Keys — stable and meaningful (not index for dynamic/reorderable lists)?
- Context splits — one giant context causing unrelated consumers to re-render?
- Expensive children — rendered unconditionally when they could be gated?
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 Changed · +1 lines 588c04908d53
- 4d ago First seen · 132 lines · 43 tokens per session scan A f98fa85b9130
review-perf is a command published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 1,929 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 2026-09-03.
Other commands, from other repositories
artifact_fetch.rs
In the dmg the Tauri webview origin is https://tauri.localhost (HTTPS) while the local backend serves on http://localhost:8000 (HTTP). WKWebView classifies any HTTP subresource loaded from an HTTPS document as "active mixed content" and blocks it silently — both iframe loads and fetch() from JS. The artifact panel…
test-bar
Generate a floating QA test overlay for the current branch's UI changes. Use when user says /test-bar, needs visual QA scenarios, or wants to test conditional rendering paths.
integration-audit
Perform a comprehensive audit of all features, checking whether each feature is fully integrated across every layer of the stack (frontend UI, API routes, database/Supabase, state management, types). Output the results as an interactive HTML visualization using the Factory-inspired design system.
web-build-fix
Diagnose and resolve web build, bundling, or deployment issues.
react-build
Fix React build failures (Vite, webpack, Next.js, CRA, Parcel, esbuild, Bun) incrementally — JSX/TSX compile errors, hydration mismatches, server/client component boundary failures, missing types. Invokes the react-build-resolver agent for minimal, surgical fixes.
svelte:storybook-troubleshoot
Diagnose and fix common Storybook issues in SvelteKit projects, including build errors, module problems, and configuration issues.