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 commands/iwritec0de/app-dev/perfgit clone --depth 1 https://github.com/iwritec0de/app-devWhat 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 | $0.00010 | $0.00992 |
| Opus 5 | $0.00005 | $0.00496 |
| Sonnet 5 | $0.00002 | $0.00198 |
| Haiku 4.5 | $0.00001 | $0.00099 |
Grade A, and why
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 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next.js Performance
Analyze bundle size, identify heavy dependencies, and check Core Web Vitals readiness.
Load the nextjs-expert skill for performance optimization patterns.
Usage
/perf [--bundle] [--vitals]
Arguments
Parse $ARGUMENTS to extract:
- --bundle — Focus on bundle size analysis
- --vitals — Focus on Core Web Vitals readiness
- No flags = run both
Instructions
Bundle Analysis
1. Check for Bundle Analyzer
grep -q "@next/bundle-analyzer" package.json && echo "installed" || echo "not installed"
If not installed, recommend:
npm install -D @next/bundle-analyzer
2. Analyze Build Output
If a .next directory exists from a recent build:
ls -lhS .next/static/chunks/*.js 2>/dev/null | head -20
If no build exists, suggest running npm run build and reading the output.
3. Dependency Impact Analysis
Search for heavy client-side imports:
# Check for heavy libs in client components
grep -r "'use client'" --include="*.tsx" --include="*.ts" -l
For each client component, check imports for known heavy packages:
moment(330KB) → suggestdayjs(2KB) ordate-fnslodash(72KB) → suggestlodash-eswith tree shaking or individual imports@fortawesome/fontawesome(1.5MB) → suggestlucide-reactor@heroiconschart.js(200KB) → suggest wrapping innext/dynamicthree.js(600KB) → must be dynamically imported@mui/material— Check if tree-shaking properly (named imports)axios(13KB) → nativefetchworks in Next.js
4. Image Optimization Check
grep -rn "<img " --include="*.tsx" --include="*.jsx" | grep -v "node_modules"
grep -rn "next/image" --include="*.tsx" --include="*.jsx" | head -5
Report:
- Number of
<img>tags (should be zero — usenext/image) - Missing
width/heightorfillonImagecomponents - Missing
sizesprop on responsive images - Large images without
priorityon above-the-fold content
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 · 139 lines · 10 tokens per session scan A 8da9df13182b
perf is a command published in the GitHub repository iwritec0de/app-dev (3 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 992 once invoked, about $0.0001 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 commands, from other repositories
battlecard
Create a sales-ready competitive battlecard — positioning, feature comparison, objection handling, and win strategies.
better-auth:add-plugin
Add a better-auth plugin to an existing project. Configures server and client plugins with proper imports.
sheet-report
Analyze a Numbers or Excel file and generate a report with charts.
numbers-to-excel
Convert a Numbers document to Excel.
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
add-skill
Add a new Skill to the current plugin with proper structure.