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 skills add fusengine/agents --skill php-quality-toolinggit clone --depth 1 https://github.com/fusengine/agentsWrote 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/skills/fusengine/agents/php-quality-tooling)<a href="https://agentmods.dev/skills/fusengine/agents/php-quality-tooling"><img src="https://agentmods.dev/badge/skills/fusengine/agents/php-quality-tooling/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fusengine/agents/php-quality-tooling"><img src="https://agentmods.dev/badge/skills/fusengine/agents/php-quality-tooling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.01392 |
| Opus 5.5 | $0.00020 | $0.00557 |
| Sonnet 5.5 | $0.00010 | $0.00278 |
| Haiku 4.5 | $0.00005 | $0.00139 |
Grade A, and why
php-quality-tooling 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 22d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Includes a decision guide for greenfield vs legacy codebases (PHPStan level + baseline strategy, Rector's withPhpSets()/withPhpLevel(), PHP-CS-Fixer rule sets), plus ready-to-copy templates for phpstan.neon, rector.php, .php-cs-fixer.dist.php, and a composer-scripts CI pipeline.
Do NOT use this skill on Laravel projects — Laravel uses Pint (a thin wrapper over PHP-CS-Fixer) and Larastan instead, both owned by laravel-expert. Do NOT use it for test framework setup (php-testing) or language syntax questions (php-language-modern).
PHP Quality Tooling
Three complementary tools. PHPStan finds type bugs, Rector rewrites code (upgrades + refactors), PHP-CS-Fixer formats to a coding standard. They do not overlap — run all three.
Agent Workflow (MANDATORY)
Before ANY implementation, spawn 3 agents in parallel, one Agent call each with a name:
- fuse-ai-pilot:explore-codebase - Detect existing config (phpstan.neon, rector.php, .php-cs-fixer.dist.php), PHP version in composer.json
- fuse-ai-pilot:research-expert - Verify latest PHPStan/Rector/PHP-CS-Fixer docs via Context7/Exa
- mcp__context7__query-docs - Check current config API surface
After implementation, run fuse-ai-pilot:sniper for validation.
Overview
| Tool | Role | Config file | Verdict |
|---|---|---|---|
| PHPStan | Static analysis (type safety, dead code) | phpstan.neon |
Reports errors, never edits |
| Rector | Automated upgrade + refactor | rector.php |
Rewrites source |
| PHP-CS-Fixer | Coding-standard formatter | .php-cs-fixer.dist.php |
Rewrites whitespace/style |
Scope note: Laravel Pint is a thin opinionated wrapper around PHP-CS-Fixer. On a Laravel project use Pint (→ laravel-expert); everywhere else use PHP-CS-Fixer directly, which is what this skill covers.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 22d ago Changed f69f32970e68
- 1mo ago Changed 82c55942c3ec
- 1mo ago First seen · 126 lines · 51 tokens per session scan A 8a742fd8b5aa
php-quality-tooling is a skill published in the GitHub repository fusengine/agents (33 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 1,392 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
php-cleanup
This skill should be used when the user asks to "find unused PHP code", "clean up dead code", "find unused Composer dependencies", "find unused imports", "remove dead PHP code", "run composer unused", "check for missing dependencies", "detect unused classes", "detect unused methods", "clean up use statements", "audit…
shiny-py-optimize
Diagnose and fix performance problems in Shiny for Python apps — slow startup, sluggish interactions, blocking operations, and apps that struggle beyond a handful of concurrent users. Use when a Shiny for Python app is slow, hangs, recomputes too much, times out, or must support more users; when the user asks to…
phx-investigate
Investigate Elixir/Phoenix bugs root-cause first. Reproduce failures, cite evidence, and use optional Amp subagents only when useful.
phx-trace
Use when debugging how a value or request reaches Elixir code, finding who calls a function, or planning a signature change. Builds the call tree with mix xref callers instead of reading files one by one.
craftcms
Craft CMS 5 plugin and module development — extending Craft with PHP. Covers elements, element queries, services, models, records, controllers, migrations, queue jobs, console commands, field types, native fields, events, behaviors, Twig extensions, widgets, filesystems, permissions, project config, GraphQL, testing…
craft-php-guidelines
Craft CMS 5 PHP coding standards and conventions. ALWAYS load when writing, editing, reviewing, or discussing any PHP in a Craft plugin or module — even small edits. Also when running ECS, PHPStan, or scaffolding with ddev craft make. Covers: PHPDoc blocks (@author, @since, @throws chains), section headers…