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/basher83/lunar-claudeWrote 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/basher83/lunar-claude/review-uv-script)<a href="https://agentmods.dev/commands/basher83/lunar-claude/review-uv-script"><img src="https://agentmods.dev/badge/commands/basher83/lunar-claude/review-uv-script.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 5.1 | $0.00013 | $0.02046 |
| Opus 5 | $0.00006 | $0.01023 |
| Sonnet 5 | $0.00003 | $0.00409 |
| Haiku 4.5 | $0.00001 | $0.00205 |
Grade A, and why
review-uv-script scanned grade A with 1 finding 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 8d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Flag `subprocess.run(..., shell=True)` with user input How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UV Python Script Review
Review the uv Python script at $ARGUMENTS against best practices.
Script to Review
@$ARGUMENTS
Confidence Scoring
Rate each potential issue from 0-100:
| Score | Meaning |
|---|---|
| 0-25 | Likely false positive or stylistic preference |
| 26-50 | Minor nitpick, not explicitly in best practices |
| 51-75 | Valid but low-impact issue |
| 76-90 | Important issue requiring attention |
| 91-100 | Critical bug or explicit best practice violation |
Only report issues with confidence ≥ 80. Quality over quantity.
Review Categories
1. PEP 723 Metadata Block (Critical)
Required elements:
- Has
# /// scriptopening marker (exactly/// script, not/// scriptsor//) - Has
# ///closing marker requires-pythonis specified (e.g.,>=3.11)dependenciesarray is present (even if empty)- Each TOML line starts with
#
Forbidden patterns:
[tool.uv.metadata]- Invalid field, causes runtime error- Custom top-level fields (
author,version,description) - Onlyrequires-pythonanddependenciesallowed - Missing
#prefix on TOML lines
Valid [tool.uv] usage (without .metadata):
# /// script
# requires-python = ">=3.11"
# dependencies = []
# [tool.uv]
# exclude-newer = "2025-01-01T00:00:00Z" # Valid
# ///
2. Shebang Line (Important)
- Has proper shebang:
#!/usr/bin/env -S uv run --script - Consider
--quietflag for production scripts - Shebang must be first line (before metadata block)
3. Dependency Management (Important)
Version pinning:
- Use
>=X.Y.Zfor utilities (allows updates) - Use
==X.Y.Zonly for deployment scripts requiring reproducibility - No bare package names (
"httpx"→"httpx>=0.27.0")
Heavy dependencies flag:
- Flag
tensorflow,torch,transformers- Too heavy for single-file scripts - Suggest using proper uv project instead
4. Documentation (Medium)
- Module docstring present after metadata block
- Docstring includes: purpose, usage, examples
- Metadata (team, author, version) in docstring, NOT in TOML
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.
- 8d ago First seen · 295 lines · 13 tokens per session scan A 1569cced9bca
review-uv-script is a command published in the GitHub repository basher83/lunar-claude (22 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 2,046 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
notebook-review
Comprehensive review of Jupyter notebooks and Python scripts.
python-review
Comprehensive Python code review for PEP 8 compliance, type hints, security, and Pythonic idioms. Invokes the python-reviewer agent.
review-react-code
A command that reviews React and TypeScript code, including how components are organised, how Hooks are used, how state is handled, and how the code performs.
review-python-code
A command for reviewing Python code for style, type annotations, reliability, performance, and project rules. PEP 8 is the commonly used guide for formatting and writing readable Python.
py-harden
Scan Python backend code for anti-patterns and fix them. Runs the full anti-pattern catalog (AP-01 through AP-22) against the codebase.
py-structure
Analyze and recommend project structure improvements. Checks file sizes, layer organization, module splitting, and hexagonal architecture compliance.