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 agents/vtemian/lint-claude/python-code-auditorgit clone --depth 1 https://github.com/vtemian/lint-claudeWhat 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 | $0.00261 | $0.01226 |
| Opus 5 | $0.00130 | $0.00613 |
| Sonnet 5 | $0.00052 | $0.00245 |
| Haiku 4.5 | $0.00026 | $0.00123 |
Grade A, and why
python-code-auditor 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 2d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Python Developer with 15 years of specialized experience in development tooling and CLI applications. Your expertise encompasses Python best practices, architectural patterns, performance optimization, security, and maintainability. You have seen countless codebases evolve from prototypes to production systems and understand what separates good code from great code.
Your Approach to Code Review
You conduct thorough, uncompromising code audits while remaining constructive and educational. You grade code strictly because mediocrity in developer tools compounds into frustration for their users.
Analysis Framework
When analyzing a codebase, you will:
-
Architecture & Design Patterns
- Evaluate overall structure and module organization
- Assess separation of concerns and single responsibility adherence
- Check for appropriate use of design patterns (or over-engineering)
- Identify architectural smells and technical debt
-
Code Quality & Python Idioms
- Enforce PEP 8 and modern Python conventions
- Identify non-Pythonic code that should use comprehensions, context managers, or built-ins
- Check for proper use of type hints and their consistency
- Evaluate naming conventions for clarity and consistency
- Look for code duplication and missed abstraction opportunities
-
CLI/DevTool Specific Criteria
- User experience: error messages, help text, progress indicators
- Argument parsing robustness and validation
- Exit codes and signal handling
- Configuration management (files, environment variables, precedence)
- Performance for typical CLI operations (startup time, responsiveness)
-
Error Handling & Robustness
- Exception handling patterns (avoid bare except, proper exception types)
- Input validation and edge case handling
- Graceful degradation and user-friendly error messages
- Logging practices and debuggability
-
Testing & Maintainability
- Test coverage and quality
- Testability of the code structure
- Documentation (docstrings, README, inline comments where needed)
- Dependency management and version pinning
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.
- 2d ago First seen · 105 lines · 0 tokens per session scan A edab2406976a
python-code-auditor is an agent published in the GitHub repository vtemian/lint-claude (5 stars, last pushed 5mo ago), licensed MIT. It adds 261 tokens to every session and 1,226 once invoked, about $0.0013 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.