polyfill-reviewer

polyfill-reviewer is an agent for Claude Code from hmj1026/dhpk. It costs 129 tokens per session (1,330 once invoked), scanned A, original, MIT.

An automatic reviewer for PHP compatibility code that behaves differently across runtime versions. It checks edited files containing version guards, which are conditions that select code based on the installed PHP version or available features.

In plain words
What is it for?
Use it after editing PHP polyfills or version-conditional code; use a separate audit for a complete version matrix across many files.
Why use it?
It catches compatibility risks after guarded PHP code changes and ensures the supported version combinations are considered before replying.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; $skill-name invocation.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dhpk plugin — 39 skills, 1 command, 1 agent, 3 hooks shipped together

Good fit Use it after editing PHP polyfills or version-conditional code; use a separate audit for a complete version matrix across many files.

Compare 6 agents from other repositories ↓
View source ↗ hmj1026/dhpk
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add hmj1026/dhpk
Claude Code
/plugin install dhpk

Made for: Claude Code.

Or install dhpk, the plugin that ships this one along with the rest of its 39 skills, 1 command, 1 agent, 3 hooks.

Wrote 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.

agentmods badge for polyfill-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hmj1026/dhpk/polyfill-reviewer/github.svg)](https://agentmods.dev/agents/hmj1026/dhpk/polyfill-reviewer)
Your own site
<a href="https://agentmods.dev/agents/hmj1026/dhpk/polyfill-reviewer"><img src="https://agentmods.dev/badge/agents/hmj1026/dhpk/polyfill-reviewer/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.

agentmods 80×15 button for polyfill-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/hmj1026/dhpk/polyfill-reviewer"><img src="https://agentmods.dev/badge/agents/hmj1026/dhpk/polyfill-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,330 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00129 $0.01330
Opus 5.5 $0.00052 $0.00532
Sonnet 5.5 $0.00026 $0.00266
Haiku 4.5 $0.00013 $0.00133

Measured yesterday against content hash 5d61eaa38f14, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

polyfill-reviewer 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 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.

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.

generated/claude-marketplace/package/modules/library-author/agents/polyfill-reviewer.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Polyfill Reviewer

Recommended review of polyfill branches after every guard-bearing change. The standard code / db / sec / frontend / doc reviewers do not reason about version trees; this reviewer fills that gap.

Use cx / gitnexus per ${CLAUDE_PLUGIN_ROOT}/rules/tool-routing.md, not bulk Read.

Trigger

The orchestrator dispatches this reviewer when the changed-file scope covers a .php file whose body matches the guard_patterns regex from module.yaml. The supplied scope is authoritative; do not infer the path set from hooks or marker files.

When NOT

  • Deep audit of one guard across all files → skill $library-author polyfill-audit (manual $library-author polyfill-audit)
  • Diff blast-radius across the full version matrix → version-matrix-impact-reviewer

Process

  1. Read inputs (in order):

    • Review Request scope → list of edited paths.
    • composer.json → require constraints for deps with || across majors. This is the declared matrix.
    • .github/workflows/*.yml → strategy.matrix block. This is the executed matrix. Note include: / exclude: modifiers.
    • phpunit.xml → testsuites (which dirs run on which suite).
    • For each edited file: git log --follow --oneline -10 <file> → asymmetric edit history.
  2. Enumerate every guard in the diff. For each version_compare / class_exists / interface_exists / method_exists / InstalledVersions::satisfies / PHP_VERSION_ID occurrence, classify per the table in library-author polyfill-audit skill (do not duplicate the table here — Read that skill for the classification logic).

  3. Map branches to matrix cells. For each branch, list the matrix cells that could enter it (cell deps satisfy the guard's condition).

  4. Cross with test coverage. For each branch, find a test that demonstrably exercises it. Smoke tests ("no exception thrown") are NOT evidence — both branches pass them trivially.

  5. Asymmetric-edit detection. From the git log, if a recent commit touched the new-major branch but not the symmetric old-major branch (or vice versa), flag it. State which branch was changed, which was not, and what semantic divergence the edit might have introduced.

Read the full file on GitHub · 128 lines

Changes

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.

  1. yesterday Changed · -1 tokens per session 5d61eaa38f14
  2. 10d ago Changed · -35 lines · -38 tokens per session 235ed84c8b22
  3. 1mo ago Changed · -3 lines · -1 tokens per session 4dcf32757604
  4. 1mo ago Changed · +29 lines 52943e9491b8
  5. 1mo ago First seen · 137 lines · 169 tokens per session scan A 3a790ab70e21

Subscribe to this mod's changes

polyfill-reviewer is an agent published in the GitHub repository hmj1026/dhpk (2 stars, last pushed today), licensed MIT. It adds 129 tokens to every session and 1,330 once invoked, about $0.0005 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 2026-09-05.

Related

Other agents, from other repositories

symfony-reviewer

Reviews Symfony code for quality, architecture, and best practices. Use proactively after code modifications to check controller thickness, value object usage, service coupling, and Symfony conventions. Triggers on code review, quality audit, or architecture check requests.

dev-toolings/superpowers-symfony · 52 tokens

laravel-reviewer

Laravel 13 and PHP 8.3+ (8.5 recommended) code review specialist — Actions pattern, Pest PHP, Eloquent, Sanctum, AI SDK, performance optimization.

TheBeardedBearSAS/claude-craft · 42 tokens

symfony-engineer

Implements Symfony application code following framework best practices, drawing on the superpowers-symfony skill library. Use for general Symfony coding — controllers, services, dependency injection, value objects/DTOs, forms, Twig components, configuration — when no more specialized agent (api-platform-builder…

dev-toolings/superpowers-symfony · 76 tokens

pattern-auditor

Design patterns audit coordinator. Orchestrates stability, behavioral, creational, integration, and GoF structural pattern auditors. Use PROACTIVELY for distributed systems, resilience, and design pattern audits.

dykyi-roman/awesome-claude-code · 45 tokens

gof-structural-auditor

GoF Structural patterns auditor. Analyzes Adapter, Facade, Proxy, Composite, Bridge, and Flyweight patterns. Called by acc:pattern-auditor coordinator.

dykyi-roman/awesome-claude-code · 44 tokens

laravel-simplifier

Simplifies and refines PHP/Laravel code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

laravel/agent-skills · 39 tokens