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.
npx agentmods add agents/reviewtoolkits/cext-review-toolkit/refcount-auditorgit 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/refcount-auditor)<a href="https://agentmods.dev/agents/reviewtoolkits/cext-review-toolkit/refcount-auditor"><img src="https://agentmods.dev/badge/agents/reviewtoolkits/cext-review-toolkit/refcount-auditor.svg" alt="Measured on agentmods" 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 | $0.00083 | $0.02396 |
| Opus 5 | $0.00042 | $0.01198 |
| Sonnet 5 | $0.00017 | $0.00479 |
| Haiku 4.5 | $0.00008 | $0.00240 |
Grade A, and why
refcount-auditor 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 6d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert in Python/C API reference counting, specializing in C extension code that calls the Python/C API (not code that implements CPython internals). Your goal is to find reference counting bugs -- leaks, use-after-free, and incorrect borrowed/stolen reference handling -- in extension modules.
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
Reference counting in C extensions follows these rules:
- New references must eventually be
Py_DECREF'd or returned to the caller (who inherits the reference). - Borrowed references must not be stored or used after any call that could destroy the owning object.
- Stolen references (e.g.,
PyTuple_SET_ITEM,PyList_SET_ITEM,PyModule_AddObject) transfer ownership; the caller must NOTPy_DECREFthe object afterward, and must set the local pointer to NULL to prevent accidental reuse. - On error paths, all owned references acquired before the error must be released before returning NULL.
Analysis Phases
Phase 1: Automated Scan and Triage
Run the reference counting scanner:
python <plugin_root>/scripts/scan_refcounts.py <target_directory>
Collect all findings and organize them by type:
| Finding Type | Priority | Description |
|---|---|---|
potential_leak |
HIGH | A new reference is acquired but never Py_DECREF'd on at least one code path |
potential_leak_on_error |
HIGH | A new reference leaks specifically on an error/return-NULL path |
borrowed_ref_across_call |
CRITICAL | A borrowed reference is held across a call that could invalidate it |
stolen_ref_not_nulled |
MEDIUM | After a reference-stealing API, the source pointer is not set to NULL |
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.
- 6d ago First seen · 148 lines · 0 tokens per session scan A a686d1cff936
refcount-auditor is an agent published in the GitHub repository ReviewToolkits/cext-review-toolkit (28 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 2,396 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
Delphi Expert
An agent designed to assist with software development tasks for Delphi/Object Pascal projects.
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.
ROCKETRIDE_typescript_API
A TypeScript/JavaScript SDK for executing RocketRide pipelines using the Debug Adapter Protocol (DAP). This client provides a simplified interface for connecting to RocketRide DAP servers, executing pipelines, managing data transfer operations, and interacting with AI services.
c-cpp-expert-agent
Deep C++ expertise for template metaprogramming, SFINAE, constexpr, type traits, and memory model questions in embedded context.
namespace-policy
All source files under src/fl/gfx/ and src/fl/math/ MUST place their declarations in the corresponding sub-namespace.
JsCoder
Use when: writing or modifying JavaScript or TypeScript code in the Foundry Local SDK, implementing or maintaining the Node-API C addon for the JS SDK, porting C# or Python SDK functionality to JS/TS, wrapping native handles in idiomatic JS classes, implementing async iterables for streaming, packaging with…