health

health is a command for Claude Code from ReviewToolkits/cpython-review-toolkit. It costs 9 tokens per session (1,113 once invoked), scanned A, original, MIT.

A summary dashboard for the health of CPython’s C code. It combines results from several focused checks into status, scores, finding counts, and top issues.

In plain words
What is it for?
Use it to get a project-wide or scoped summary of reference-counting safety, recursion guards, destructor errors, uninitialized cleanup, initialization bypasses, and related checks.
Why use it?
It gives a quick overview before a detailed investigation, so developers can see which safety areas need attention first. Duplicate reports of the same issue are counted once.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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

Made for: Claude Code.

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 health

README.md
[![agentmods](https://agentmods.dev/badge/commands/reviewtoolkits/cpython-review-toolkit/health.svg)](https://agentmods.dev/commands/reviewtoolkits/cpython-review-toolkit/health)
Your own site
<a href="https://agentmods.dev/commands/reviewtoolkits/cpython-review-toolkit/health"><img src="https://agentmods.dev/badge/commands/reviewtoolkits/cpython-review-toolkit/health.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,113 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 5.1 $0.00009 $0.01113
Opus 5 $0.00005 $0.00557
Sonnet 5 $0.00002 $0.00223
Haiku 4.5 $0.00001 $0.00111

Measured 6d ago against content hash 0784330acc16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

health 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.

plugins/cpython-review-toolkit/commands/health.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CPython C Code Health Dashboard

Run all agents in summary mode to produce a quick health dashboard. Each agent reports only its top-level findings — no deep analysis.

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

Workflow

  1. Identify CPython project root (look for Include/Python.h and Objects/object.c)
  2. Run include-graph-mapper first (structural context for all other agents)
  3. Run all remaining agents with context, requesting summary-tier output only. Run at most 2 concurrently to limit memory usage.
  4. Deduplicate before scoring: when the same issue is flagged by multiple agents, count it once.
  5. Synthesize into a health dashboard:
# CPython C Code Health Dashboard

| Dimension          | Status      | Score | FIX | Top Finding                    |
|--------------------|-------------|-------|-----|--------------------------------|
| Refcount Safety    | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| Recursion Guards   | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| Destructor PyErr   | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| Uninit Dealloc     | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| Init Bypass        | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| FT Data Races      | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| STW Safety         | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| Lock Discipline    | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| Error Handling     | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| GIL Discipline     | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| Complexity         | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| NULL Safety        | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| PEP 7 Style        | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| API Deprecation    | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| Macro Hygiene      | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| Memory Patterns    | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| Include Graph      | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| Change Velocity    | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |
| Fix Quality        | 🟢/🟡/🔴  | X/10  | N   | [1-line summary]               |

## Overall Health: X/10

## Top 3 Priorities
1. [Most impactful improvement]
2. [Next]
3. [Next]

For detailed analysis, run:
  /cpython-review-toolkit:explore . [aspect] deep

Read the full file on GitHub · 81 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. 6d ago First seen · 81 lines · 9 tokens per session scan A 0784330acc16

Subscribe to this mod's changes

health is a command published in the GitHub repository ReviewToolkits/cpython-review-toolkit (10 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 1,113 once invoked, about $0.0000 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.

Related

Other commands, from other repositories

qa-changes

This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…

OpenHands/extensions · 63 tokens

doctor

Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…

doncheli/don-cheli-sdd · 76 tokens

fix

Universal debugging and fix application with semantic code analysis.

stefan-jansen/claude-code-toolkit · 9 tokens

gh-issue-use-cypress

Like /gh-issue-use-browser, but pinned to the Cypress MCP — use when your project runs the Cypress MCP for browser automation. Example — /gh-issue-use-cypress "Composer > Save" saving toasts failure but the record persists.

skyfox675/agents-skills · 49 tokens

http-service

Build, review or debug a Bun HTTP service. Loads the http-service skill, then works the task through its workflow.

MadAppGang/magus · 27 tokens

auditar-cascading

Invoca cascading-failures-auditor — audita serviço para 5 triggers de cascade (sem timeout, retry sem jitter, sem circuit breaker, sem deadline, queue unbounded) e gera CASCADING-AUDIT.md.

luanpdd/kit-mcp · 54 tokens