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 skills/vurakit/agentup/phpnpx skills add vurakit/agentup --skill phpgit clone --depth 1 https://github.com/vurakit/agentupWhat 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 | $0.00109 | $0.01927 |
| Opus 5 | $0.00055 | $0.00963 |
| Sonnet 5 | $0.00022 | $0.00385 |
| Haiku 4.5 | $0.00011 | $0.00193 |
Grade A, and why
php-pro-max 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PHP Pro Max - Backend Generator
When User Requests PHP Work
Follow this workflow for every PHP-related task:
1. Analyze Requirements
Extract from the user's request:
- Project type: REST API, web app, microservice, CMS, e-commerce, CLI
- Domain: web, database, queue, messaging, real-time
- Constraints: specific framework? PHP version? Docker? cloud?
- Scale: small project, enterprise, SaaS
Default Stack (always use unless user specifies otherwise)
| Component | Default | Package |
|---|---|---|
| Framework | Laravel 11 | laravel/laravel |
| Database | MySQL 8 | illuminate/database (Eloquent) |
| Auth | JWT | tymon/jwt-auth or Laravel Sanctum |
| Cache | Redis | predis/predis |
| Queue | Redis/Database | Laravel Queue |
| Config | ENV vars | .env + config/*.php |
| Deploy | Docker Compose | Dockerfile + docker-compose.yml |
Project structure: Laravel standard layout:
app/Http/Controllers/ — HTTP controllers
app/Http/Middleware/ — request middleware
app/Http/Requests/ — form request validation
app/Models/ — Eloquent models
app/Services/ — business logic
app/Repositories/ — data access layer
app/Exceptions/ — custom exceptions
config/ — configuration files
database/migrations/ — database migrations
database/seeders/ — database seeders
routes/api.php — API routes
routes/web.php — web routes
resources/views/ — Blade templates
tests/Unit/ — unit tests
tests/Feature/ — feature tests
2. Generate Architecture System (REQUIRED for new projects)
python3 skills/php/scripts/search.py "<project description>" --arch-system -p "ProjectName"
What ships with it
28 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.
- data/anti-patterns.csv 19 KB
- data/architecture.csv 11 KB
- data/dependency.csv 9.4 KB
- data/error-handling.csv 21 KB
- data/idioms.csv 20 KB
- data/interfaces.csv 18 KB
- data/packages.csv 6.4 KB
- data/patterns.csv 31 KB
- data/performance.csv 17 KB
- data/php-reasoning.csv 6.0 KB
- data/security.csv 19 KB
- data/stacks/api-platform.csv 6.3 KB
- data/stacks/codeigniter.csv 8.2 KB
- data/stacks/database.csv 11 KB
- data/stacks/laravel.csv 28 KB
- data/stacks/livewire.csv 8.7 KB
- data/stacks/queue.csv 11 KB
- data/stacks/slim.csv 6.7 KB
- data/stacks/symfony.csv 14 KB
- data/testing.csv 17 KB
- data/tooling.csv 8.5 KB
- scripts/arch_system.py 12 KB runs code
- scripts/core.py 14 KB runs code
- scripts/search.py 5.1 KB runs code
- templates/base/quick-reference.md 3.2 KB
- templates/base/skill-content.md 3.9 KB
- templates/platforms/antigravity-skill.md 8.1 KB
- templates/platforms/antigravity.json 1.0 KB
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 · 242 lines · 109 tokens per session scan A 9332b5e205fa
php-pro-max is a skill published in the GitHub repository vurakit/agentup (56 stars, last pushed 5mo ago), licensed MIT. It adds 109 tokens to every session and 1,927 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…