explore

A command for examining CPython’s C source code, using separate checks for areas such as memory use, errors, threading, complexity, and style.

In plain words
What is it for?
Use it to review the whole CPython project or a selected file, directory, or module for specific code-quality and safety concerns.
Why use it?
It helps break a large C codebase into focused reviews instead of requiring one person to inspect every kind of risk at once.

Command

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.

agentmods
npx agentmods add commands/reviewtoolkits/cpython-review-toolkit/explore
Clone the repo
git clone --depth 1 https://github.com/ReviewToolkits/cpython-review-toolkit
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00012 $0.02183
Opus 5 $0.00006 $0.01092
Sonnet 5 $0.00002 $0.00437
Haiku 4.5 $0.00001 $0.00218

Measured 2d ago against content hash a60077641fe3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explore 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 2d 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/cpython-review-toolkit/commands/explore.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Comprehensive CPython C Code Exploration

Run a comprehensive analysis of CPython C source code using multiple specialized agents, each focusing on a different aspect of C code quality. The include-graph-mapper runs first to provide structural context for all subsequent agents.

Arguments: "$ARGUMENTS"

Argument Parsing

Parse arguments into three categories:

Scope (path or glob):

  • . or omitted → entire project (default)
  • Objects/ → specific directory tree
  • Objects/listobject.c → specific file
  • Modules/_io/ → specific module

Aspects (which agents to run):

  • includes → include-graph-mapper only
  • refcounts → refcount-auditor
  • errors → error-path-analyzer
  • gil → gil-discipline-checker
  • complexity → c-complexity-analyzer
  • style → pep7-style-checker
  • null-safety → null-safety-scanner
  • deprecation → api-deprecation-tracker
  • macros → macro-hygiene-reviewer
  • memory → memory-pattern-analyzer
  • recursion → recursion-guard-auditor
  • pyerr-clear → pyerr-clear-auditor
  • uninit-dealloc → uninitialized-dealloc-auditor
  • ft-races → ft-race-scanner
  • stw-safety → stw-safety-checker
  • lock-discipline → lock-discipline-checker
  • init-bypass → init-bypass-checker
  • parity → parity-checker
  • history → git-history-analyzer
  • all → all agents (default)

Note: recursion, pyerr-clear, uninit-dealloc, ft-races, stw-safety, and lock-discipline, and init-bypass are the tree-sitter-based detectors (require pip install tree-sitter tree-sitter-c). The tsan-report-analyzer, tsan-stress-generator, and oom-reproducer agents are on-demand dynamic tools (they need a built interpreter — a --disable-gil+TSan build, or a build providing _testcapi.set_nomemory), not part of the static explore pipeline; see the reproduce command.

Options:

  • deep → full detail, no output truncation
  • summary → summary tier only (faster)
  • parallel → run agents concurrently where possible
  • --max-parallel N → cap concurrent agents per group (default: 2)

Read the full file on GitHub · 246 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. 2d ago First seen · 246 lines · 12 tokens per session scan A a60077641fe3

Subscribe to this mod's changes

explore is a command published in the GitHub repository ReviewToolkits/cpython-review-toolkit (10 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 2,183 once invoked, about $0.0001 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 2026-08-31.