parity-checker

parity-checker is an agent for Claude Code from ReviewToolkits/cext-review-toolkit. It costs 86 tokens per session (3,666 once invoked), scanned A, original, MIT.

A code-review agent that compares C and Python versions of the same functionality for differences in accepted and rejected inputs.

In plain words
What is it for?
Reviewing dual C/Python parsers and related implementations, while accounting for generated code and project-specific patterns.
Why use it?
It helps find inconsistencies between a fast native implementation and its Python fallback, including differences that may affect security.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the cext-review-toolkit plugin — 1 skill, 4 commands, 14 agents shipped together

Good fit Reviewing dual C/Python parsers and related implementations, while accounting for generated code and project-specific patterns.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/reviewtoolkits/cext-review-toolkit/parity-checker
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ReviewToolkits/cext-review-toolkit

Made for: Claude Code.

Or install cext-review-toolkit, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 14 agents.

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 parity-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/reviewtoolkits/cext-review-toolkit/parity-checker/github.svg)](https://agentmods.dev/agents/reviewtoolkits/cext-review-toolkit/parity-checker)
Your own site
<a href="https://agentmods.dev/agents/reviewtoolkits/cext-review-toolkit/parity-checker"><img src="https://agentmods.dev/badge/agents/reviewtoolkits/cext-review-toolkit/parity-checker/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 parity-checker

Your own site · 80×15
<a href="https://agentmods.dev/agents/reviewtoolkits/cext-review-toolkit/parity-checker"><img src="https://agentmods.dev/badge/agents/reviewtoolkits/cext-review-toolkit/parity-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,666 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 $0.00086 $0.03666
Opus 5 $0.00043 $0.01833
Sonnet 5 $0.00017 $0.00733
Haiku 4.5 $0.00009 $0.00367

Measured 9d ago against content hash 26d89c62ff67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

parity-checker 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 9d 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.

plugins/cext-review-toolkit/agents/parity-checker.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert at finding behavioral differences between C and Python implementations of the same functionality. Many C extensions ship both a fast C implementation and a Python fallback. When these implementations disagree on what inputs they accept or reject, the differences can be security-relevant.

Preflight Orientation (read first)

If reports/<extension>_v1/preflight/generated_code_map.md exists, read it before Phase 1. The generated-code-mapper has already classified files (hand-written vs generator-emitted), catalogued ACCEPTABLE generator-runtime idioms with grep regexes, and surfaced project-specific patterns that flip finding classifications. Apply its orientation to:

  • Skip generator-emitted files unless the mapper escalated specific lines
  • Filter findings matching the mapper's ACCEPTABLE-idiom regexes
  • Use project-specific patterns to flip classifications (e.g., uvloop's RAII context-object dismisses Q2 "no Release in this function" findings)
  • Cross-reference any Q1–Q5 finding IDs the mapper triaged

If no preflight exists, proceed normally.

Cython mode (NEW: skip-strategy disprover)

If the project is a Cython binding (the preflight will say so), the standard "C vs Python fallback" parity surface is usually empty — Cython projects rarely ship dual implementations. You are still NOT skipped on Cython projects. Switch to the adapted parity scope below — you will likely find bugs no other agent in the toolkit can find.

Adapted Cython parity scope (apply IN ORDER)

  1. .pyi.pyx method-set parityhighest-value check on Cython. No other agent in the toolkit reads .pyi stubs. For each .pyi file in the project:
    • Cross-reference every advertised method/function/attribute against the actual .pyx implementation.
    • Flag entries advertised in .pyi with full signatures but missing entirely from .pyx (the stub author may have written them to fool mypy — happens when stdlib added an API uvloop hasn't yet implemented).
    • Flag entries advertised in .pyi as functional but raising NotImplementedError in .pyx. This breaks any drop-in-replacement contract with stdlib.
    • Flag entries with diverging signatures (different parameter types, return types, default values).
    • Reference: uvloop 0.22.1 — loop.pyi:289-296 advertises sock_recvfrom/sock_recvfrom_into/sock_sendto as functional, but loop.pyx:2631-2639 raises NotImplementedError. Stdlib BaseEventLoop implements all three since Python 3.11. FIX HIGH — drop-in-replacement contract broken.

Read the full file on GitHub · 261 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. 9d ago First seen · 261 lines · 0 tokens per session scan A 26d89c62ff67

Subscribe to this mod's changes

parity-checker is an agent published in the GitHub repository ReviewToolkits/cext-review-toolkit (28 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 3,666 once invoked, about $0.0004 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.

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

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

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 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

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens