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 skills/shareai-lab/learn-claude-code/code-reviewnpx skills add shareAI-lab/learn-claude-code --skill code-reviewgit clone --depth 1 https://github.com/shareAI-lab/learn-claude-codeWhat 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 | $0.00035 | $0.01103 |
| Opus 5 | $0.00017 | $0.00551 |
| Sonnet 5 | $0.00007 | $0.00221 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
os.system(f"ls {user_input}") Copies of this mod
8 near-identical copies found in the catalogue:
- code-review — 100% identical, 0 lines differ
- code-review — 100% identical, 0 lines differ
- code-review — 100% identical, 0 lines differ
- code-review — 100% identical, 0 lines differ
- code-review — 100% identical, 0 lines differ
- code-review — 100% identical, 0 lines differ
- code-review — 100% identical, 0 lines differ
- code-review — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Skill
You now have expertise in conducting comprehensive code reviews. Follow this structured approach:
Review Checklist
1. Security (Critical)
Check for:
- Injection vulnerabilities: SQL, command, XSS, template injection
- Authentication issues: Hardcoded credentials, weak auth
- Authorization flaws: Missing access controls, IDOR
- Data exposure: Sensitive data in logs, error messages
- Cryptography: Weak algorithms, improper key management
- Dependencies: Known vulnerabilities (check with
npm audit,pip-audit)
# Quick security scans
npm audit # Node.js
pip-audit # Python
cargo audit # Rust
grep -r "password\|secret\|api_key" --include="*.py" --include="*.js"
2. Correctness
Check for:
- Logic errors: Off-by-one, null handling, edge cases
- Race conditions: Concurrent access without synchronization
- Resource leaks: Unclosed files, connections, memory
- Error handling: Swallowed exceptions, missing error paths
- Type safety: Implicit conversions, any types
3. Performance
Check for:
- N+1 queries: Database calls in loops
- Memory issues: Large allocations, retained references
- Blocking operations: Sync I/O in async code
- Inefficient algorithms: O(n^2) when O(n) possible
- Missing caching: Repeated expensive computations
4. Maintainability
Check for:
- Naming: Clear, consistent, descriptive
- Complexity: Functions > 50 lines, deep nesting > 3 levels
- Duplication: Copy-pasted code blocks
- Dead code: Unused imports, unreachable branches
- Comments: Outdated, redundant, or missing where needed
5. Testing
Check for:
- Coverage: Critical paths tested
- Edge cases: Null, empty, boundary values
- Mocking: External dependencies isolated
- Assertions: Meaningful, specific checks
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 · 158 lines · 35 tokens per session scan A a64c8c43b496
code-review is a skill published in the GitHub repository shareAI-lab/learn-claude-code (75,835 stars, last pushed 6d ago), licensed MIT. It adds 35 tokens to every session and 1,103 once invoked, about $0.0002 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 skills, from other repositories
haiku-master
How to write a proper haiku. Use when the user asks for a haiku.
landing-page
How to design a landing page. Use when the user asks to build a website or marketing page.
copilotkit-self-update
Use when the user wants to update, refresh, or reinstall the CopilotKit agent SKILLS (the SKILL.md files that teach this agent about CopilotKit). NOT for updating the CopilotKit codebase or project — this is specifically about refreshing the skills/knowledge this agent has loaded. Triggers on "update copilotkit…
high-end-visual-design
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
edu-math-tutorial
数学题分步讲解视频的领域知识。适用场景：(1) 用户给出一道数学题并要求做讲解/ 解题视频；(2) 用户说"讲解这道题"、"生成解题视频"、"make a math tutorial"； (3) 需要中文数学教学视频，涉及方程、公式或几何图形。本 skill 只提供领域 知识（题目拆解、讲解节奏、旁白文案规范、版式与 KaTeX 排版风格）；画面、 配音与成片一律用 Creator 原生 Element 与工具从源头构建。.
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…