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 commands/reviewtoolkits/cpython-review-toolkit/hotspotsgit clone --depth 1 https://github.com/ReviewToolkits/cpython-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/commands/reviewtoolkits/cpython-review-toolkit/hotspots)<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>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 | $0.00015 | $0.01060 |
| Opus 5 | $0.00008 | $0.00530 |
| Sonnet 5 | $0.00003 | $0.00212 |
| Haiku 4.5 | $0.00002 | $0.00106 |
Grade A, and why
hotspots scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CPython C Code Hotspots
Run the highest-value agents to find the worst functions to fix first: the crash-class detectors plus c-complexity-analyzer, refcount-auditor, and error-path-analyzer. Answers the question: "Where should I focus my review efforts?"
Scope: "$ARGUMENTS" (default: entire project)
Workflow
- Identify CPython project root
- Run include-graph-mapper first (structural context)
- 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
- 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]
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.
- 4d ago First seen · 94 lines · 15 tokens per session scan A dc8eb79516f4
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.