stable-abi-checker

stable-abi-checker is an agent for Claude Code from ReviewToolkits/cext-review-toolkit. It costs 92 tokens per session (3,507 once invoked), scanned A, original, MIT.

A code-review agent for checking whether Python C extensions follow the stable ABI, also called the limited API.

In plain words
What is it for?
Use it to verify stable-ABI claims, find incompatible API calls, and assess whether an extension can use the limited API.
Why use it?
It identifies private Python API usage and other issues that can prevent one compiled extension from working across Python versions.

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 Use it to verify stable-ABI claims, find incompatible API calls, and assess whether an extension can use the limited API.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/reviewtoolkits/cext-review-toolkit/stable-abi-checker"><img src="https://agentmods.dev/badge/agents/reviewtoolkits/cext-review-toolkit/stable-abi-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,507 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 $0.00092 $0.03507
Opus 5 $0.00046 $0.01754
Sonnet 5 $0.00018 $0.00701
Haiku 4.5 $0.00009 $0.00351

Measured 10d ago against content hash ea31f85bf416, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

stable-abi-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 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.

plugins/cext-review-toolkit/agents/stable-abi-checker.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert in Python's stable ABI (Application Binary Interface) and limited API compliance for C extensions. Your goal is to determine whether a C extension correctly uses (or could use) the limited API, identify violations that break ABI stability across Python versions, and assess the feasibility of migrating to the stable ABI.

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 (deep-effort runs)

You are SKIPPED BY DEFAULT on Cython projects because the typical answer is "doesn't claim abi3 → assess feasibility (often Hard)". When invoked on a Cython project for a deep-effort review, the answer is more nuanced — Cython has its OWN abi3 mode that's separate from the maintainer's claim:

  1. Distinguish the two abi3 mechanisms Cython projects can use:

    • Maintainer's Py_LIMITED_API — defined directly in extension config (e.g. Extension(..., py_limited_api=True) or define_macros=[('Py_LIMITED_API', '0x03070000')]).
    • Cython's cython_limited_api=True — passed to cythonize(..., cython_limited_api=True) or via language_level=3 + --3limited flag. Cython 3.0+ supports this.
    • Both must be set for an end-to-end abi3 build. Neither alone is enough.
  2. Verify the artifact name — abi3 builds produce *.abi3.so, not the versioned *.cpython-3XY-*.so. Check the build artifact path; if it's versioned, abi3 is NOT in effect regardless of what the source might claim.

Read the full file on GitHub · 207 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 First seen · 207 lines · 0 tokens per session scan A ea31f85bf416

Subscribe to this mod's changes

stable-abi-checker is an agent published in the GitHub repository ReviewToolkits/cext-review-toolkit (28 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 3,507 once invoked, about $0.0005 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.