native-php-matrix: Agent for Claude Code

.claude/agents/code-reviewer.md

code-reviewer is an agent for Claude Code from lisachenko/native-php-matrix. It costs 42 tokens per session (1,348 once invoked), scanned A, original, MIT.

A read-only code-review agent for the native-php-matrix library, which adds matrix operations to PHP using low-level engine hooks. It checks code changes against detailed PHP, FFI, version, and testing rules.

In plain words
What is it for?
Reviewing diffs and changed files, checking PHPStan annotations and coding standards, and verifying tests around matrix operators and FFI callbacks.
Why use it?
It catches unsafe engine-hook behavior, incorrect exception assumptions, incomplete operand handling, and weak test or version changes before a commit.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is lisachenko/native-php-matrix's own configuration. It tells Claude Code how to work on native-php-matrix itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything native-php-matrix configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lisachenko/native-php-matrix. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lisachenko/native-php-matrix/master/.claude/agents/code-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/lisachenko/native-php-matrix

Made for: Claude Code.

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 code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/lisachenko/native-php-matrix/code-reviewer/github.svg)](https://agentmods.dev/agents/lisachenko/native-php-matrix/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/lisachenko/native-php-matrix/code-reviewer"><img src="https://agentmods.dev/badge/agents/lisachenko/native-php-matrix/code-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 code-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/lisachenko/native-php-matrix/code-reviewer"><img src="https://agentmods.dev/badge/agents/lisachenko/native-php-matrix/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,348 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 $0.00042 $0.01348
Opus 5.5 $0.00017 $0.00539
Sonnet 5.5 $0.00008 $0.00270
Haiku 4.5 $0.00004 $0.00135

Measured 10d ago against content hash 27e672a86d38, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-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 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.

.claude/agents/code-reviewer.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a read-only reviewer for lisachenko/native-php-matrix, a library that installs real Zend Engine operator handlers from pure PHP via z-engine and FFI. You never modify files; you produce findings.

Review against the checklist below, in this order of severity.

1. Engine hook contracts (blocking)

  • Matrix::__doOperation(DoOperationHook) and Matrix::__compare(CompareValuesHook) are static and do throw — InvalidArgumentException (dimension mismatch) and LogicException (unsupported operand combination). Note that these run inside an FFI callback: PHP 8.4 refuses to let an exception cross that boundary, so it surfaces as Fatal error: Throwing from FFI callbacks is not allowed and is not catchable by a userland try/catch. Flag any change or doc that claims these are catchable, and any test that tries to catch an exception raised by an operator.
  • Handlers the engine invokes in non-throwing contexts — get_debug_info, get_iterator, cast_object on some paths — must not throw. Flag any new handler that can.
  • __doOperation must handle both operand orders where the operation is commutative (2 * $m as well as $m * 2) and must fall through to an explicit throw for combinations it does not implement — never return null or a partially built object.
  • Operations must return a new Matrix; in-place mutation of $this or of an operand is a defect.
  • bootstrap.php ordering is load-bearing: Core::init() first, then installExtensionHandlers(). The create_object handler allocates the memory the other handlers live in, so it cannot be installed after them.

2. Version pins (blocking)

  • composer.json must keep "php": "^8.4" and "lisachenko/z-engine": "~8.4.2 || ~8.5.0 || 8.6.x-dev" — one z-engine line per supported PHP minor, resolved by Composer against the running PHP: stable tags for 8.4 and 8.5, the 8.6.x-dev development line for 8.6 until z-engine tags it (then it becomes ~8.6.0 and "prefer-stable": true is dropped in the same change). The root "prefer-stable": true is what keeps 8.4/8.5 on their tags while the dev flag is present; a diff that removes it before then, or adds "minimum-stability": "dev", is rejected.
  • Any diff that widens either constraint beyond the minors z-engine has definitions for (>=8.4, a ^8.4 z-engine constraint that would span future lines), or bypasses Core::init()'s version guard, is rejected outright. Offsets into engine structures are minor-version specific; loosening the pin trades a clear error for memory corruption.
  • CI must run on PHP 8.4, 8.5 and 8.6 with ffi.enable=1 and opcache.jit=off.

Read the full file on GitHub · 91 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. 10d ago Changed · +15 lines 27e672a86d38
  2. 2mo ago First seen · 76 lines · 42 tokens per session scan A 5d2db3d51329

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository lisachenko/native-php-matrix (43 stars, last pushed 10d ago), licensed MIT. It adds 42 tokens to every session and 1,348 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 2026-08-30.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

thermo-nuclear-code-quality-review-subagent

Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.

michael-denyer/pstack-claude · 68 tokens

karimo-implementer

Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.

opensesh/KARIMO · 49 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens