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/ReviewToolkits/cext-review-toolkitWrote 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/reviewtoolkits/cext-review-toolkit/parity-checker)<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.
<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>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 | $0.00086 | $0.03666 |
| Opus 5 | $0.00043 | $0.01833 |
| Sonnet 5 | $0.00017 | $0.00733 |
| Haiku 4.5 | $0.00009 | $0.00367 |
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.
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)
.pyi↔.pyxmethod-set parity — highest-value check on Cython. No other agent in the toolkit reads.pyistubs. For each.pyifile in the project:- Cross-reference every advertised method/function/attribute against the actual
.pyximplementation. - Flag entries advertised in
.pyiwith 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
.pyias functional but raisingNotImplementedErrorin.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:289-296advertisessock_recvfrom/sock_recvfrom_into/sock_sendtoas functional, butloop.pyx:2631-2639raisesNotImplementedError. StdlibBaseEventLoopimplements all three since Python 3.11. FIX HIGH — drop-in-replacement contract broken.
- Cross-reference every advertised method/function/attribute against the actual
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.
- 9d ago First seen · 261 lines · 0 tokens per session scan A 26d89c62ff67
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.
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.
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…
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…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
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.