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 skills add mickeyyaya/refactoring-skills --skill ai-generated-code-reviewgit clone --depth 1 https://github.com/mickeyyaya/refactoring-skillsWrote 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/skills/mickeyyaya/refactoring-skills/ai-generated-code-review)<a href="https://agentmods.dev/skills/mickeyyaya/refactoring-skills/ai-generated-code-review"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/ai-generated-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/skills/mickeyyaya/refactoring-skills/ai-generated-code-review"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/ai-generated-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 | $0.00066 | $0.03930 |
| Opus 5 | $0.00033 | $0.01965 |
| Sonnet 5 | $0.00013 | $0.00786 |
| Haiku 4.5 | $0.00007 | $0.00393 |
Grade A, and why
ai-generated-code-review 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.get(url, timeout=5) How it starts
The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-Generated Code Review
Overview
AI-generated code fails differently than human-written code. An LLM will confidently invent a plausible-looking method that doesn't exist; it skips auth because tutorials rarely include it.
The core problem: Syntactically fluent but semantically unreliable. It passes linters and type checkers yet silently calls methods that don't exist or leaves security-critical paths unguarded.
When to use: Any PR with AI assistance markers — unusually consistent formatting, generic variable names, verbose boilerplate, comments explaining obvious things.
Mindset shift: Don't ask "is this correct?" Ask "did the AI understand the actual requirements, or generate plausible code for a slightly different problem?"
Quick Reference — AI Code Smell Severity
| Smell | Severity | Primary Signal |
|---|---|---|
| Hallucinated API | Critical | Method/package does not exist in the installed version |
| Missing authorization | Critical | No ownership or role check on resource access |
| Plausible-but-wrong logic | High | Code runs, wrong result — passes review but fails in prod |
| Shallow error handling | High | catch (e) {}, except: pass, swallowed errors |
| Copy-paste context mismatch | High | Code from wrong framework, version, or language idiom |
| Missing edge cases | Medium | Happy-path only — nil, empty, overflow, concurrent access |
| Over-abstraction | Medium | Factory/strategy/decorator for a 10-line function |
| Outdated patterns | Medium | Deprecated API, old library version idiom |
AI Code Smells Catalog
Smell 1: Hallucinated API Calls
LLM invents method names that sound plausible but don't exist. Common in: date/time libraries, ORMs, SDK clients, testing utilities.
Signals:
- Method names that read naturally but produce
TypeError/AttributeErrorat runtime - Chained calls on objects that don't support them
- Named parameters that the function signature doesn't define
- Package imports from libraries that don't exist on PyPI/npm/pkg.go.dev
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.
- 9d ago First seen · 387 lines · 66 tokens per session scan A c62a2ef746dd
ai-generated-code-review is a skill published in the GitHub repository mickeyyaya/refactoring-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 3,930 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
council-review
Multi-model validation council — auto-validate plans, architecture changes, and PRs via validate-plan/review before executing.
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.
craft-goal
Compile or lint a persistent Mayor-style goal prompt that ratchets a bead graph through bounded RPI experiments toward one larger outcome. Triggers: "craft a goal prompt", "mayor goal", "goal-runner prompt", "lint this goal", "is this goal safe". (Shaping one experiment's intent routes to plan.).
huggingface-best
Find and compare recommended Hugging Face models for a task using benchmarks, model size, and device constraints. Use for model selection questions; use huggingface-local-models for GGUF setup and hf-cli for Hub operations.
submit-github-pr
Use when publishing an existing TensorRT-Model-Connect change as a GitHub pull request. Verifies authenticated repository access, branch and diff scope, validation evidence, commit identity, reviewer-facing text, exact pushed head, and the created draft PR without merging it.