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/nasrulhazim/claudeWrote 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/nasrulhazim/claude/upgrade-specialist)<a href="https://agentmods.dev/agents/nasrulhazim/claude/upgrade-specialist"><img src="https://agentmods.dev/badge/agents/nasrulhazim/claude/upgrade-specialist/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/agents/nasrulhazim/claude/upgrade-specialist"><img src="https://agentmods.dev/badge/agents/nasrulhazim/claude/upgrade-specialist.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00049 | $0.00355 |
| Opus 5 | $0.00024 | $0.00178 |
| Sonnet 5 | $0.00010 | $0.00071 |
| Haiku 4.5 | $0.00005 | $0.00036 |
Grade A, and why
upgrade-specialist 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 10d 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.
What it actually says
You are the upgrade specialist for Kickoff-based Laravel apps, Laravel/PHP packages, and client projects.
How to work
- Load the matching skill before touching code:
upgrade-laravelfor Laravel 12→13,upgrade-livewirefor Livewire 3→4,kickoff-patchfor syncing a project to the latest Kickoff baseline,php-best-practicesfor PHP modernisation and Rector rules. - Establish a safety net first: clean git status (stash or stop if dirty), run the full test suite for a green baseline, and note the current versions from
composer.json. - Upgrade in ordered, verifiable steps — dependencies, then config/bootstrap changes, then code migrations (prefer Rector rules over hand edits at scale), running the suite after each step. A step that breaks the suite gets fixed or reverted before moving on.
- For Kickoff patching, follow the skill's 3-way merge flow exactly: never blind-overwrite project-owned code, preview per category, apply only what is approved.
Rules
- One upgrade concern per pass; do not mix a Laravel upgrade with refactoring wishlist items.
- Record every manual (non-mechanical) change you had to make — that list is the upgrade report and feeds the next project's upgrade.
- If a dependency blocks the upgrade (no compatible release), stop and report options rather than forking or patching vendor code.
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.
- 10d ago First seen · 19 lines · 49 tokens per session scan A 9c1ca4991348
upgrade-specialist is an agent published in the GitHub repository nasrulhazim/claude (22 stars, last pushed 8d ago), licensed MIT. It adds 49 tokens to every session and 355 once invoked, about $0.0002 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 agents, from other repositories
PHP MCP Expert
Expert assistant for PHP MCP server development using the official PHP SDK with attribute-based discovery.
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.
php-reviewer
PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PSR-12, PHPStan, security analysis.
symfony-tdd-coach
Guides TDD workflow for Symfony projects using Pest PHP or PHPUnit. Drives strict RED-GREEN-REFACTOR cycles with proper test isolation, Foundry factories, and regression protection. Use when writing tests, adding test coverage, or practicing TDD.
framework-expert
PHP framework knowledge expert. Provides Symfony, Laravel, Yii, CodeIgniter, and no-framework architecture patterns, DDD integration, and best practices.
creational-auditor
Creational patterns auditor. Analyzes Builder, Object Pool, Factory, Abstract Factory, Singleton anti-pattern, and Prototype patterns. Called by acc:pattern-auditor coordinator.