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/thebeardedbearsas/claude-craft/analyze-performancegit clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craftWrote 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/thebeardedbearsas/claude-craft/analyze-performance)<a href="https://agentmods.dev/commands/thebeardedbearsas/claude-craft/analyze-performance"><img src="https://agentmods.dev/badge/commands/thebeardedbearsas/claude-craft/analyze-performance.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 | $0.00003 | $0.02152 |
| Opus 5 | $0.00002 | $0.01076 |
| Sonnet 5 | $0.00001 | $0.00430 |
| Haiku 4.5 | $0.00000 | $0.00215 |
Grade A, and why
analyze-performance 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 2d 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyse Performance Flutter
Tu es un expert performance Flutter. Tu dois analyser les performances de l'application, identifier les problèmes (jank, memory leaks, rebuilds inutiles) et proposer des optimisations.
Arguments
$ARGUMENTS
Arguments :
- (Optionnel) Focus : rendering, memory, network, all
Exemple : /flutter:analyze-performance rendering
MISSION
Étape 1 : Collecte des Métriques
# Lancer en mode profile
flutter run --profile
# DevTools
flutter pub global activate devtools
dart devtools
# Analyser le code
dart analyze --fatal-infos
Étape 2 : Analyse du Rendering
Identifier les Rebuilds Inutiles
// Ajouter dans main.dart pour debug
import 'package:flutter/rendering.dart';
void main() {
debugProfileBuildsEnabled = true; // Log les builds
debugPrintRebuildDirtyWidgets = true; // Log les rebuilds
runApp(const MyApp());
}
Problèmes Courants et Solutions
1. Rebuilds en Cascade
// ❌ MAUVAIS - Tout rebuild à chaque changement
class ParentWidget extends StatelessWidget {
@override
Widget build(BuildContext context) {
return Consumer<MyModel>(
builder: (context, model, _) => Column(
children: [
HeaderWidget(title: model.title),
BodyWidget(items: model.items),
FooterWidget(), // Rebuild inutile!
],
),
);
}
}
// ✅ BON - Granularité fine
class ParentWidget extends StatelessWidget {
@override
Widget build(BuildContext context) {
return Column(
children: [
Selector<MyModel, String>(
selector: (_, model) => model.title,
builder: (_, title, __) => HeaderWidget(title: title),
),
Selector<MyModel, List<Item>>(
selector: (_, model) => model.items,
builder: (_, items, __) => BodyWidget(items: items),
),
const FooterWidget(), // const = pas de rebuild
],
);
}
}
2. ListView Non Optimisée
// ❌ MAUVAIS - Crée tous les widgets d'un coup
ListView(
children: items.map((item) => ItemWidget(item: item)).toList(),
)
// ✅ BON - Lazy loading
ListView.builder(
itemCount: items.length,
itemBuilder: (context, index) => ItemWidget(item: items[index]),
// Optimisations supplémentaires
cacheExtent: 500, // Pré-render
addAutomaticKeepAlives: false, // Si pas besoin de garder l'état
)
// ✅ ENCORE MIEUX - Avec taille fixe
ListView.builder(
itemCount: items.length,
itemExtent: 80, // Hauteur fixe = calcul optimisé
itemBuilder: (context, index) => ItemWidget(item: items[index]),
)
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.
- 2d ago First seen · 358 lines · 3 tokens per session scan A 8c611f18375f
analyze-performance is a command published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 3d ago), licensed MIT. It adds 3 tokens to every session and 2,152 once invoked, about $0.0000 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
health-check
Run diagnostics on Claude Code toolkit configuration and status.
safe-decompile
Safely fingerprint and decompile an Android artifact through the sandboxed MCP server.
gradle-build
Fix Gradle build errors for Android and KMP projects.
bootstrap
Verifies and repairs the Claude Code Toolkit installation.
debug
Diagnose and fix a bug or failing test in VisionAgent.
checklist
Generate a custom checklist for the current feature based on user requirements.