hotspots

hotspots is a command for coding agents from ReviewToolkits/cpython-review-toolkit. It costs 15 tokens per session (1,060 once invoked), scanned A, original, MIT.

A command that finds high-risk and hard-to-maintain functions in CPython’s C source code. It checks areas such as reference counting, error handling, recursion, and code complexity.

In plain words
What is it for?
Use it to locate likely crashes, memory-management mistakes, error-path bugs, and complex functions in a CPython project. It can examine the whole project or a specified scope.
Why use it?
It helps answer where a code review should start instead of requiring developers to inspect the whole project equally. It groups findings into a prioritized hotspot report.

Command

Part of the cpython-review-toolkit plugin — 7 commands, 23 agents shipped together

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/hotspots
Clone the repo
git clone --depth 1 https://github.com/ReviewToolkits/cpython-review-toolkit

Or install cpython-review-toolkit, the plugin that ships this one along with the rest of its 7 commands, 23 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 hotspots

README.md
[![agentmods](https://agentmods.dev/badge/commands/reviewtoolkits/cpython-review-toolkit/hotspots.svg)](https://agentmods.dev/commands/reviewtoolkits/cpython-review-toolkit/hotspots)
Your own site
<a href="https://agentmods.dev/commands/reviewtoolkits/cpython-review-toolkit/hotspots"><img src="https://agentmods.dev/badge/commands/reviewtoolkits/cpython-review-toolkit/hotspots.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,060 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 $0.00015 $0.01060
Opus 5 $0.00008 $0.00530
Sonnet 5 $0.00003 $0.00212
Haiku 4.5 $0.00002 $0.00106

Measured 4d ago against content hash dc8eb79516f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hotspots 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 4d 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/hotspots.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CPython C Code Hotspots

Run the highest-value agents to find the worst functions to fix first: the crash-class detectors plus c-complexity-analyzer, refcount-auditor, and error-path-analyzer. Answers the question: "Where should I focus my review efforts?"

Scope: "$ARGUMENTS" (default: entire project)

Workflow

  1. Identify CPython project root
  2. Run include-graph-mapper first (structural context)
  3. Run with at most 2 agents in parallel, feeding context:
    • recursion-guard-auditor — native-stack-overflow SIGSEGV in recursion-prone slots
    • pyerr-clear-auditor — exception-clobber in the destructor family
    • uninitialized-dealloc-auditor — half-built object freed on an error path
    • init-bypass-checker — NULL field deref after __new__ bypass / a deletable member
    • refcount-auditor — find reference counting errors
    • error-path-analyzer — find error handling bugs
    • c-complexity-analyzer — find the hardest-to-maintain code
  4. Synthesize into a prioritized hotspot report:
# CPython C Code Hotspots

## Critical Issues (FIX)
[Refcount leaks, NULL dereferences, error handling bugs]
- [agent]: Issue in `function` (file.c:line)

## Complexity Hotspots
_Relative threshold: top 2% by score (`hotspot_threshold` from the script).
Extraction coverage: N%._

| Rank | Function | File | Score | Lines | Gotos | Top Issue |
|------|----------|------|-------|-------|-------|-----------|
| 1    | func     | f.c  | 7.3   | 450   | 28    | Deep nesting |

## Manual Cleanup Ladders (goto-free cleanup burden)
| Rank | Function | File | Ladder | Owned locals | Returns w/ cleanup |
|------|----------|------|--------|--------------|--------------------|
| 1    | func     | f.c  | 78     | 6            | 13                 |

## Error-Prone Functions
[Functions appearing in BOTH a crash-class agent's findings and either
complexity list — the intersection is the real priority]

## Recommended Fix Order
1. [Highest-impact fix]
2. [Next]
3. [Next]

Read the full file on GitHub · 94 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. 4d ago First seen · 94 lines · 15 tokens per session scan A dc8eb79516f4

Subscribe to this mod's changes

hotspots is a command published in the GitHub repository ReviewToolkits/cpython-review-toolkit (10 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,060 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.