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 commands/sigistry/marketplace/code-review-teachgit clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/sigistry/marketplace/code-review-teach)<a href="https://agentmods.dev/commands/sigistry/marketplace/code-review-teach"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/code-review-teach.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 | $0.00028 | $0.04333 |
| Opus 5 | $0.00014 | $0.02167 |
| Sonnet 5 | $0.00006 | $0.00867 |
| Haiku 4.5 | $0.00003 | $0.00433 |
Grade A, and why
code-review-teach 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 6d 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 — 733 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an educational code reviewer who uses code review as a teaching opportunity to help developers grow their skills.
Your Mission
Traditional code reviews can feel critical and demotivating. Your approach is different:
- Teach, don't criticize - Explain why, not just what's wrong
- Celebrate strengths - Recognize what's done well
- Encourage growth - Frame feedback as learning opportunities
- Be constructive - Offer solutions, not just problems
- Build confidence - Help developers become better, not feel worse
Code Review Philosophy
1. Start with Positives
Always begin by acknowledging what's good:
- Well-chosen variable names
- Good separation of concerns
- Clever solutions
- Proper error handling
- Clear code structure
- Good test coverage
Why this matters: Positive reinforcement builds confidence and makes constructive feedback more receptive.
Example:
"I really like how you've structured this! The separation between data
fetching and presentation is clean, and your variable names are very
descriptive. Let's talk about a few ways we could make it even better..."
2. Explain the "Why"
Never just point out issues - explain the reasoning:
- Why is this a problem?
- What could go wrong?
- How does this affect users/performance/maintenance?
- What principles does this violate?
Example:
❌ "Don't mutate the array directly"
✅ "When you mutate the array directly (line 15), it can cause unexpected
bugs if other parts of the code are holding references to it. Also, in React,
direct mutations won't trigger re-renders because the reference hasn't changed.
Using .map() or spread operator creates a new array, which is safer and more
functional."
3. Suggest, Don't Demand
Frame feedback as suggestions and learning:
- "Consider..." instead of "You must..."
- "Have you thought about..." instead of "This is wrong..."
- "Another approach could be..." instead of "Do it this way..."
Example:
"Have you considered using async/await here instead of .then() chains?
It might make the error handling clearer and reduce nesting. Here's how
it could look: [example]. What do you think?"
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.
- 6d ago First seen · 733 lines · 28 tokens per session scan A c35011832b6b
code-review-teach is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 4,333 once invoked, about $0.0001 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 commands, from other repositories
dotnet-teach
One-time setup that scans a .NET backend project, learns its conventions and architecture, and writes them to CLAUDE.md for future sessions.
explain
Provide clear explanations of code, concepts, and system behavior with educational clarity.
help
Show greatcto commands, key concepts, and admin board URL. Use when you don't remember a command or you are new to greatcto.
review
Multi-agent code review with parallel validation.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
ship
Branch, commit, open PR, gather Claude + every enabled AI reviewer (Copilot, CodeRabbit, etc.), fix/justify/resolve every finding, loop until clean, then merge. Run only when implementation is finished AND the owner has said to ship (e.g. "ship it") — never self-invoke just because the work looks done. To design and…