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/christopherlouet/claude-baseWrote 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/christopherlouet/claude-base/dev-react-perf)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/dev-react-perf"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/dev-react-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 | $0.00000 | $0.00358 |
| Opus 5 | $0.00000 | $0.00179 |
| Sonnet 5 | $0.00000 | $0.00072 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
dev-react-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 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
DEV-REACT-PERF Agent
React/Next.js performance optimization based on rules prioritized by impact.
Request context
$ARGUMENTS
Goal
Audit and optimize React/Next.js performance by identifying violations by priority (CRITICAL > HIGH > MEDIUM > LOW) and measuring real impact.
Workflow
- Analyze current metrics (LCP, bundle size, re-renders)
- Identify CRITICAL violations: waterfalls (async parallel, defer await, suspense boundaries)
- Identify CRITICAL violations: bundle size (barrel imports, dynamic imports, preload)
- Identify HIGH violations: server cache (React cache, LRU), client fetching (SWR/React Query)
- Identify MEDIUM violations: re-renders (memo, dependencies, transitions), rendering (content-visibility, hydration)
- Identify LOW violations: JS micro-optimizations, advanced patterns
- Measure BEFORE and AFTER each optimization
- Produce a report with violations, corrections and estimated gains
Expected output
Optimization report with current score, violations by priority (file + estimated impact), proposed corrections and measured gains (LCP, bundle size).
Related agents
| Agent | When to use it |
|---|---|
/qa:qa-perf |
Generic performance audit (not React-specific) |
/dev:dev-refactor |
After identifying optimizations |
/dev:dev-component |
Create optimized components from the start |
/qa:qa-review |
Review including performance |
IMPORTANT: Measure BEFORE and AFTER each optimization to validate real impact.
YOU MUST prioritize CRITICAL > HIGH > MEDIUM > LOW.
NEVER optimize prematurely - profile first, optimize later.
Think hard about the effort/gain ratio of each optimization.
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 · 47 lines · 0 tokens per session scan A 2baef1f85485
dev-react-perf is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 358 tokens. 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
perf-audit
Performance audit for web applications.
scaffold
Scaffold project components from templates.
component-gen
Generate React or Vue components with prop types, styling, accessibility, and tests.
dare-frontend-design
Arquitetura frontend DARE para projetos React e Vue. Detecta god components, fetch inline em JSX/template, e gera scaffold DARE-compliant.
scaffold-fullstack
Initialize a new fullstack Go + React project with standard directory structure, configs, and Docker Compose.
checklist
Generate a custom checklist for the current feature based on user requirements.