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/gil-discipline-checker)<a href="https://agentmods.dev/agents/reviewtoolkits/cext-review-toolkit/gil-discipline-checker"><img src="https://agentmods.dev/badge/agents/reviewtoolkits/cext-review-toolkit/gil-discipline-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/gil-discipline-checker"><img src="https://agentmods.dev/badge/agents/reviewtoolkits/cext-review-toolkit/gil-discipline-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 | $0.00108 | $0.02988 |
| Opus 5 | $0.00054 | $0.01494 |
| Sonnet 5 | $0.00022 | $0.00598 |
| Haiku 4.5 | $0.00011 | $0.00299 |
Grade A, and why
gil-discipline-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 12d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert in GIL (Global Interpreter Lock) management for C extensions, specializing in code that interacts with foreign C libraries and that must be ready for free-threaded Python (PEP 703). Your goal is to find GIL discipline violations -- calling Python APIs without the GIL, holding the GIL during blocking calls, mismatched GIL macros, and thread safety issues for the free-threaded build.
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.
Key Concepts
The GIL rules for C extensions are:
- All Python/C API calls require the GIL to be held, with very few exceptions (
Py_AddPendingCall,PyGILState_Ensure). - Py_BEGIN_ALLOW_THREADS / Py_END_ALLOW_THREADS release and reacquire the GIL. Between these macros, no Python API may be called.
- PyGILState_Ensure / PyGILState_Release are used when a non-Python thread (e.g., a foreign library callback) needs to call Python APIs.
- Blocking operations (I/O, locks, foreign library calls that may block) should release the GIL to allow other Python threads to run.
- Free-threaded Python (3.13+ with
--disable-gil) removes the GIL entirely. Extensions must be thread-safe without relying on the GIL for mutual exclusion.
Analysis Phases
Phase 1: Automated Scan and Triage
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.
- 12d ago First seen · 193 lines · 0 tokens per session scan A 9c633e6c5f12
gil-discipline-checker is an agent published in the GitHub repository ReviewToolkits/cext-review-toolkit (28 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 2,988 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.
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.
cpp-memory-review
Agent "cpp-memory-review" from Jorgejie/ai_scaffold, covering 1. {{t "cppmemoryreview.jnireftitle"}}, 2. {{t "cppmemoryreview.heaptitle"}}, 3. {{t "cppmemoryreview.buffertitle"}}, 4. {{t "cppmemoryreview.sensitivetitle"}} and 5. {{t "cppmemoryreview.rationalitytitle"}}.
cpp-dev
MUST BE USED for C++ code review and refactoring. HFT-grade C++20 specialist. Catches UB, memory bugs, latency killers, cache inefficiencies. Invoke with "refactor for maintainability" for plans saved to .claude/plans/.
cpp-hunter
C++ bug hunter for memory corruption, UB, concurrency issues. Paranoid interrogator who demands proof. Hypothesis-driven. Hunt only - no fixes.
refcount-auditor
Use this agent to find reference counting errors in CPython C source code — the.
api-deprecation-tracker
Use this agent to track deprecated C API usage within CPython's own code. Finds usage of deprecated APIs like PyModuleAddObject, PyUnicodeREADY, PyUNICODE, old buffer protocol, and other APIs that have newer replacements.\n\n \nContext: The user wants to find deprecated API usage.\nuser: "What deprecated C APIs are…