Borrowing it
Nothing to install: this file belongs to TakaGoto/rag-learning-academy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TakaGoto/rag-learning-academy/main/.claude/skills/code-review/SKILL.mdgit clone --depth 1 https://github.com/TakaGoto/rag-learning-academyWrote 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/takagoto/rag-learning-academy/code-review)<a href="https://agentmods.dev/skills/takagoto/rag-learning-academy/code-review"><img src="https://agentmods.dev/badge/skills/takagoto/rag-learning-academy/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/takagoto/rag-learning-academy/code-review"><img src="https://agentmods.dev/badge/skills/takagoto/rag-learning-academy/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 | $0.00011 | $0.01148 |
| Opus 5.5 | $0.00004 | $0.00459 |
| Sonnet 5.5 | $0.00002 | $0.00230 |
| Haiku 4.5 | $0.00001 | $0.00115 |
Grade A, and why
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 1mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review: Expert Feedback on Your RAG Implementation
Review the learner's RAG code with the eye of an experienced RAG engineer, providing actionable feedback that improves correctness, performance, and robustness.
Language awareness: See
.claude/LANGUAGE_AWARENESS.md.
Step 1: Identify the Code to Review
Welcome! Let's take a close look at your RAG code together.
First, determine what code is available for review:
-
If the user specifies a file or directory (e.g.,
/code-review projects/my-rag/retriever), review that. -
If no argument is given, check for a learner profile at
progress/learner-profile.mdand look for code insrc/andprojects/. -
If no RAG code exists anywhere in
projects/orsrc/(and no file was specified), guide them warmly:"It looks like you haven't written any RAG code yet — that's the perfect place to start! Run
/buildto create your first RAG component, and then come back here for expert feedback on what you've built. I'll be ready to help you level it up!"Stop here — do not continue to Step 2.
-
If code is found and multiple files exist, ask which component they want reviewed, or offer to review the full pipeline.
Step 2: Read and Understand the Code
Before giving feedback, thoroughly understand what the code does:
- Read all relevant files
- Trace the data flow from input to output
- Identify the overall architecture and design pattern
- Note which libraries and models are being used
Step 3: Review Dimensions
Evaluate the code across these dimensions, providing specific feedback for each:
Correctness
- Does the code produce correct results?
- Are there logic errors, off-by-one errors, or incorrect API usage?
- Are edge cases handled (empty input, very large documents, special characters)?
- Are embeddings and vector operations mathematically correct?
RAG-Specific Best Practices
- Chunk size and overlap: Are they appropriate for the document type and use case?
- Embedding dimensions: Do all components agree on the embedding dimension?
- Prompt engineering: Is the RAG prompt well-structured? Does it instruct the model to use only the provided context?
- Context window management: Could the context exceed the model's token limit?
- Metadata handling: Is useful metadata preserved through the pipeline?
- Error handling: What happens when the retriever returns no results? When the API is down?
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.
- 1mo ago First seen · 118 lines · 11 tokens per session scan A 187ca5039a0a
code-review is a skill published in the GitHub repository TakaGoto/rag-learning-academy (24 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 1,148 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
advisor-orchestrator-worker
Use when a task is too large for one model pass, needs parallel research or generation across many subtasks (like researching a dozen competitors at once), or the user asks to orchestrate multiple models, split work across a model team, run an advisor-worker loop, have a stronger model review the plan while cheap…
rag-code-review
When performing code review on a PR, diff, snippet, or "look at this change" request, first consult the corpus for related ADRs, coding standards, prior patterns, and similar files. Grounds review comments in the team's actual decisions instead of generic best practices. Trigger on any review-style request — "review"…
rag-techniques-contribution-guidelines
Checks a RAGTechniques pull request against the repository's contribution guidelines (CONTRIBUTING.md): where new technique notebooks go, the README list entry and table row every new technique needs, the required notebook structure, and notebook hygiene. Use on any PR that adds or changes a notebook under…
world-model-diagnostic
Twenty-minute diagnostic mapping a team to a world-model paradigm (vector DB, structured ontology, signal-fidelity). Use when you say "run the world model diagnostic", "audit our world model", "which world model architecture fits us", or "audit where we automate judgment". Use for AI readiness assessments and…
sync-codebase
A codebase indexing tool that builds searchable representations of a local Git repository, including code embeddings and a code relationship graph. Later runs update only changed files.
answer-audit
Adversarially audit a RAG answer against the corpus it claims to cite. Use when asked to review, critique, sanity-check, or "give skeptical feedback on" an answer produced by Canon (or any retrieval-grounded system) — especially when the answer looks good. Assumes the answer is wrong until each claim is proven…