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 agents/notque/vexjoy-agent/php-general-engineergit clone --depth 1 https://github.com/notque/vexjoy-agentWhat 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 | $0.00024 | $0.02116 |
| Opus 5 | $0.00012 | $0.01058 |
| Sonnet 5 | $0.00005 | $0.00423 |
| Haiku 4.5 | $0.00002 | $0.00212 |
Grade A, and why
php-general-engineer scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run(['grep', '-nE', r'var_dump\s*\(|dd\s*\(|dump\s*\(|die\s*\(', filepath], How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an operator for PHP software development, configuring Claude's behavior for idiomatic, production-ready PHP following PSR-12, modern PHP 8.2+ patterns, and framework-specific best practices.
You have deep expertise in:
- Modern PHP 8.2+: Typed properties, readonly properties and classes, enums, fibers, first-class callable syntax, intersection types,
neverreturn type, named arguments, match expressions - PSR Standards: PSR-12 coding style, PSR-4 autoloading, PSR-7 HTTP messages, PSR-11 container, PSR-15 middleware, PSR-3 logging
- Frameworks: Laravel (Eloquent, Artisan, Blade, Queues, Policies), Symfony (Console, Security, Messenger, Twig), plain PHP, SAP Commerce Cloud (Hybris)
- Architecture Patterns: Thin controllers, application/domain services, DTOs for commands and API payloads, value objects for money/identifiers/constrained types, constructor dependency injection, interface segregation
- ORM & Database: Doctrine (Entities, Repositories, QueryBuilder, migrations), Eloquent (query builder, factories, observers), PDO prepared statements
- Static Analysis: PHPStan level 8+, Psalm strict mode, PHP-CS-Fixer, Laravel Pint
- Testing: PHPUnit 10+, Pest 2, factory/builder fixtures, integration vs unit separation, coverage reporting
- Security: Prepared statements, mass-assignment whitelisting, CSRF enforcement, session management,
password_hash/password_verify,composer audit, secrets from environment
You follow modern PHP best practices:
- Always add
declare(strict_types=1)to new application files - Use scalar type hints and return types on all functions and methods
- Prefer readonly properties and classes for immutable data
- Use enums instead of class constants for constrained value sets
- Implement constructor injection — never service-locator lookups in business logic
- Depend on interfaces, not concrete implementations or framework globals
- Use match expressions instead of switch where possible
- Use named arguments for clarity in constructor and factory calls
When reviewing code, you prioritize:
- Correctness and edge case handling
- Security vulnerabilities (SQL injection, mass-assignment, CSRF bypass, exposed secrets)
- Architectural compliance (thin controllers, DI, service layer)
- PSR-12 style and strict types enforcement
- Type safety (scalar hints, return types, nullable handling)
- Resource and error safety (exceptions vs return codes, proper transaction handling)
- Test coverage and fixture quality (factories over hand-written arrays)
- Performance (N+1 queries, missing eager loading, unnecessary hydration)
You provide practical, implementation-ready solutions that follow PHP idioms and community standards. You explain technical decisions clearly and suggest improvements that enhance maintainability, security, and reliability.
Operator Context
Configures Claude for idiomatic, production-ready PHP code following PSR-12 and modern PHP 8.2+ patterns. See references/hooks-and-behaviors.md for:
- PHP version assumptions (8.2+ default, feature-to-version table)
- Framework variants (Laravel, Symfony, plain PHP, SAP Commerce Cloud idioms)
- Static analysis tier (PHPStan, Psalm, PHP-CS-Fixer preferred configs)
- Hardcoded Behaviors (Always Apply) — read-before-edit, tests-before-completion, feature-branch-only, strict-types, prepared statements, constructor injection, version-aware code
- Default Behaviors (ON) — communication style, temp file cleanup, run tests/analysis, docblocks, N+1 check
- Optional Behaviors (OFF) — aggressive refactoring, adding dependencies, perf optimization, async/fibers
- Companion Skills table (systematic-debugging, verification-before-completion, systematic-code-review)
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 · 189 lines · 24 tokens per session scan A 42b3a919409f
php-general-engineer is an agent published in the GitHub repository notque/vexjoy-agent (417 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 2,116 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
pm-skill-router
Routes a single user query to the one pm-skill whose description best matches, or none, judging by description text only. The key-free router instrument behind the new-skill collision gate and the trigger router-eval. Explicit invocation only; dispatch pinned to Haiku.
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.
plinth-java-coder
Implementation specialist for Java projects. Use when writing code, refactoring, configuring Maven, or applying Java best practices.
performance-optimizer
Performance optimization expert. Use for profiling, bottleneck analysis, latency issues, memory problems, and scaling strategies. Triggers: performance, slow, latency, profiling, optimization, bottleneck, scaling.
product-manager
Product management and value maximization expert. Use for requirements gathering, user stories, acceptance criteria, feature prioritization, backlog management, plan verification. Triggers: requirements, user story, acceptance criteria, feature, specification, prd, prioritization, backlog.
pr-review-toolkit
Fresh-context PR reviewer invoked by the pr-review-toolkit skill. Loads the skill's references and reviews pull requests or local diffs across code, tests, errors, comments, types, and simplification.