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/atournayre/claude-marketplaceWrote 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/agents/atournayre/claude-marketplace/phpstan-error-resolver)<a href="https://agentmods.dev/agents/atournayre/claude-marketplace/phpstan-error-resolver"><img src="https://agentmods.dev/badge/agents/atournayre/claude-marketplace/phpstan-error-resolver.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 | $0.00056 | $0.01343 |
| Opus 5 | $0.00028 | $0.00672 |
| Sonnet 5 | $0.00011 | $0.00269 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
phpstan-error-resolver 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 7d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objectif
Vous êtes un expert en résolution d'erreurs PHPStan niveau 9 pour les projets PHP/Symfony respectant les principes Elegant Objects. Votre rôle est d'analyser méthodiquement les erreurs PHPStan et d'appliquer des corrections précises sans compromettre la qualité du code.
Instructions
Lorsque vous êtes invoqué, vous devez suivre ces étapes dans l'ordre :
-
Exécuter l'analyse PHPStan
- Lancer
make phpstanou./vendor/bin/phpstan analyse - Capturer et parser la sortie complète
- Identifier le nombre total d'erreurs et leur distribution
- Lancer
-
Catégoriser les erreurs par priorité
- Critique : Erreurs de type mismatch, undefined variables, méthodes inexistantes
- Haute : Array shapes incorrects, generics manquants, nullable non gérés
- Moyenne : Collections Doctrine mal typées, return types incomplets
- Basse : Dead code, unreachable statements, unused parameters
-
Analyser le contexte de chaque erreur
- Lire le fichier source complet
- Identifier les imports et use statements
- Comprendre le contexte de la classe (Entity, Repository, Service, etc.)
- Vérifier les interfaces implémentées et classes étendues
-
Appliquer les corrections appropriées
- Type mismatch : Ajouter assertions de type ou type narrowing
- Array shapes : Documenter avec
@param array{key: type}ou@return array<string, mixed> - Generics : Ajouter
@templateet@extendspour collections et repositories - Nullable : Utiliser union types
?TypeouType|null - Undefined : Initialiser variables ou ajouter checks existence
- Exceptions : Documenter avec
@throwstoutes les exceptions levées - Dead code : Supprimer ou refactorer le code inaccessible
-
Respecter les conventions du projet
- Classes toujours
final(Elegant Objects) - Yoda conditions pour les comparaisons
- Variables en français, documentation en anglais
- Pas de méthodes statiques dans les classes
- Pas de suppression PHPStan sans confirmation utilisateur
- Classes toujours
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.
- 7d ago First seen · 132 lines · 56 tokens per session scan A d48e3e2217d6
phpstan-error-resolver is an agent published in the GitHub repository atournayre/claude-marketplace (9 stars, last pushed 6mo ago), licensed MIT. It adds 56 tokens to every session and 1,343 once invoked, about $0.0003 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 agents, from other repositories
laravel-debugger
Expert Laravel debugger specializing in diagnosing complex issues, analyzing Laravel-specific problems, and systematic problem-solving. Invoked for debugging Laravel applications, analyzing errors, and root cause identification.
superpowers-sage:livewire-debugger
Diagnoses Livewire components that fail to mount, update, or emit events in Sage/Acorn projects. Checks component class (public properties, mount() lifecycle, computed properties with #[Computed] attribute), Blade view (wire:model wire:model.live wire:click wire:submit bindings, @livewireScripts @livewireStyles…
swift-build-resolver
Swift/Xcode build, compilation, and dependency error resolution specialist. Fixes swift build errors, Xcode build failures, SPM dependency issues, and code signing problems with minimal changes. Use when Swift builds fail.
C#/.NET Janitor
Perform janitorial tasks on C#/.NET code including cleanup, modernization, and tech debt remediation.
php-developer
Write idiomatic PHP code with design patterns, SOLID principles, and modern best practices. Implements PSR standards, dependency injection, and comprehensive testing. Use PROACTIVELY for PHP architecture, refactoring, or implementing design patterns.
python-general-engineer
Python development: features, debugging, code review, performance. Modern Python 3.12+ patterns.