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.
git clone --depth 1 https://github.com/GoodJobwilliam/aicraftWrote 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/rules/goodjobwilliam/aicraft/mcp-code-review)<a href="https://agentmods.dev/rules/goodjobwilliam/aicraft/mcp-code-review"><img src="https://agentmods.dev/badge/rules/goodjobwilliam/aicraft/mcp-code-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/goodjobwilliam/aicraft/mcp-code-review"><img src="https://agentmods.dev/badge/rules/goodjobwilliam/aicraft/mcp-code-review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00376 | $0.00376 |
| Opus 5.5 | $0.00150 | $0.00150 |
| Sonnet 5.5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
mcp-code-review 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 2mo 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.
What it actually says
MCP Code Review Server
Professional-grade code review for your AI coding assistant. Runs entirely locally — no SaaS fees, no code uploads.
Install
The server is available as aicraft-code-review on PyPI and connects via stdio:
{
"mcpServers": {
"mcp-code-review": {
"command": "uvx",
"args": ["--from", "aicraft-code-review", "--with", "mcp<2", "mcp-code-review"]
}
}
}
Or install with pip/uv:
pip install aicraft-code-review
# or
uv tool install aicraft-code-review
Then add the server to your MCP client (Claude Code, Cursor, Cline, etc.).
Review workflow
- Run
review_codeagainst a git range (e.g.HEAD~3..HEAD) or two branches. - Filter findings by author with
--authorto focus on your own changes. - Open the generated HTML report — findings include severity ratings, file locations, and actionable fixes.
What it checks
- Deterministic local security-pattern checks (injection, deserialization, credentials, and XSS patterns)
- Bug and vulnerability detection
- N+1 query analysis
- Performance profiling (hotspots, I/O, memory)
- Style and complexity issues (configurable rules)
Tips
- Review small diffs frequently; the report is easiest to consume per-PR.
- Treat severity ratings as a queue: Critical/High first, then Medium/Low.
- The report is fully local — safe for proprietary code.
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.
- 2mo ago Changed · +27 tokens per session 86a382da596b
- 2mo ago First seen · 55 lines · 349 tokens per session scan A 697d67cdd197
mcp-code-review is a cursor rule published in the GitHub repository GoodJobwilliam/aicraft (2 stars, last pushed 1mo ago), licensed MIT. It adds 376 tokens to every session, about $0.0015 per session on Opus 5.5. 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 cursor rules, from other repositories
python-3-brutal-audit
Phase-based brutal audit workflow for Python projects - on-demand architectural review.
python-standards
Python coding standards for source files.
python
Python development guidelines — PEP 8, type hints, error handling, async patterns, packaging, and testing. Applied when working with Python code.
sweep-style
Audit xrspatial modules for PEP8 violations, unused imports, import ordering drift, and bug-prone style anti-patterns.
python-general-style
Applies general Python style guidelines including functional programming preferences and naming conventions.
code-style-and-improvements
This rule focuses on code style, refactoring suggestions, and leveraging the latest ES and Node.js features for JavaScript, TypeScript, and Python files.