ReviewToolkits

ReviewToolkits/cpython-review-toolkit

Command

Comprehensive CPython C code exploration and analysis using specialized agents.

ReviewToolkits/cpython-review-toolkit

Command

Quick health dashboard — all agents in summary mode.

ReviewToolkits/cpython-review-toolkit

Command

Find cleanup targets — complexity hotspots, refcount issues, and error handling bugs.

ReviewToolkits/cpython-review-toolkit

Command

Like explore, but INFORMED: every agent first reads a briefing of recurring CPython C bug SHAPES (sibling-hunt templates with their guarded twins), the cross-cutting triage rules, and the false-positive taxonomy — so it confirms-without-relitigating, suppresses known FPs, and hunts un-found siblings of known shapes…

ReviewToolkits/cpython-review-toolkit

Command

Cross-reference the seed catalog of previously-found CPython crashes against a fresh scan, so a fix (or a regression-after-revert) is detected. Static, drift-tolerant regression — no repros run.

ReviewToolkits/cpython-review-toolkit

Command

Quick include graph mapping — understand CPython C file structure and dependencies.

ReviewToolkits/cpython-review-toolkit

Command

Turn a static allocation-failure finding into a reproduced crash via dense OOM injection.

ReviewToolkits/cpython-review-toolkit

Agent

Toolkit v0.8.0. Target /home/danzin/projects/cpython @ 4f3be1b5777 (3.16.0a0). Builds used: /home/danzin/projects/pythonbuildmatrix/builds/{debug,release}-{gil,ft}-nojit[-asan] @ a1d580430c8. Every file cited below is byte-identical between a1d580430c8 and 4f3be1b5777 (git diff --quiet on elementtree.c, pickle.c…

ReviewToolkits/cpython-review-toolkit

Agent

Scope: the eight lines the draft had not driven to a failure — :1997 :2003 :2060 :3083 :3307 :4234 :5066 :7510 — plus a confirmation pass on the known-safe :3652.

ReviewToolkits/cpython-review-toolkit

Agent

Target ref 4f3be1b5777. Every claim below carries N/M runs and a build name; where a claim is a negative it carries the denominator that bounds it.

ReviewToolkits/cpython-review-toolkit

Agent

Slice: obj-typeobject (informed-explore) Target: /home/danzin/projects/cpython @ 4f3be1b5777 (3.16.0a0) Scope: Objects/typeobject.c only, 13,068 lines Agent: api-deprecation-tracker (+ macro-hygiene pass, not dispatched separately).

ReviewToolkits/cpython-review-toolkit

Agent

Slice: obj-typeobject (informed-explore) · Target: /home/danzin/projects/cpython @ 4f3be1b5777 (3.16.0a0) Scope: Objects/typeobject.c only, 13,068 lines Builds used: /projects/pythonbuildmatrix/builds/{debug,release}-{gil,ft}-nojit @ a1d580430c8. git diff 4f3be1b5777 a1d580430c8 -- Objects/typeobject.c…

ReviewToolkits/cpython-review-toolkit

Agent

Two low-yield-but-unassessed scanners covered in one pass. Target: CPython main 4f3be1b5777 (3.16.0a0), 14-file Objects/ sample. Both aspects produce clean negatives; the value of this report is the precision measurement and the tuning proposals, not the findings.

ReviewToolkits/cpython-review-toolkit

Agent

Covers three scanners in one pass, all of which returned 0 on the sample: scangilusage.py, scanstwsafety.py, scanlockdiscipline.py. The question for each is recall, not triage, so the Toolkit assessment is the main body.

ReviewToolkits/code-review-toolkit

Plugin Claude Code

Codebase exploration and analysis toolkit: 14 specialized agents for architecture mapping, git history analysis, consistency auditing, complexity analysis, test coverage, error handling, documentation, type design, dead code detection, tech debt inventory, pattern consistency, and API surface review.

ReviewToolkits/code-review-toolkit

Skill Claude CodeCodex

Execute the standard issue, branch, code, test, commit, PR, merge workflow for a task.

ReviewToolkits/code-review-toolkit

Instructions file

Claude Code instructions for ReviewToolkits/code-review-toolkit, covering claude.md — code-review-toolkit development guide, project overview, prerequisites, dev commands and run one test module.

ReviewToolkits/code-review-toolkit

Plugin Claude Code

Codebase exploration and analysis agents for existing code: architecture mapping, git history analysis, fix propagation detection, churn-based risk assessment, consistency auditing, complexity analysis, test coverage, error handling, documentation, project documentation accuracy, type design, dead code detection, tech.

ReviewToolkits/code-review-toolkit

Agent

Use this agent to review the public API surface of a Python project — naming consistency, parameter conventions, return type patterns, and whether the API is predictable and learnable from a user's perspective. Especially valuable for tools and libraries that have both a CLI interface and a programmatic API. This…

ReviewToolkits/code-review-toolkit

Agent

Use this agent to map the structure, dependencies, and module boundaries of a Python codebase. This is the foundational analysis agent — its output feeds into other agents as context for richer analysis. Use it when exploring an unfamiliar codebase, before running other code-review-toolkit agents, or when you need to…

ReviewToolkits/code-review-toolkit

Agent

Use this agent to find the most complex code in a Python codebase and suggest simplifications. This agent combines hotspot detection (finding where complexity concentrates) with simplification analysis (how to reduce it). It measures multiple dimensions of complexity — nesting depth, function length, parameter count…

ReviewToolkits/code-review-toolkit

Agent

Use this agent to scan a Python codebase for inconsistencies in coding patterns, style, and conventions. Unlike a PR code-reviewer that checks changes against rules, this agent compares how different parts of the codebase handle the same concerns and identifies divergence. It works both inductively (discovering…

ReviewToolkits/code-review-toolkit

Agent

Use this agent to find unused code in a Python codebase — unused imports, unreferenced functions, orphan files, unreachable branches, and stale feature flags. Dead code creates noise, increases maintenance burden, and can confuse developers into thinking unused code paths are important. This agent uses static analysis…

ReviewToolkits/code-review-toolkit

Agent

Use this agent to audit documentation quality across a Python codebase — docstrings, inline comments, module-level documentation, and README accuracy. It checks for stale comments, undocumented public APIs, misleading documentation, and comment rot. Unlike the PR-focused comment-analyzer, this agent surveys…