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/nahisaho/codegraphmcpserver/code-reviewernpx skills add nahisaho/CodeGraphMCPServer --skill code-reviewergit clone --depth 1 https://github.com/nahisaho/CodeGraphMCPServerWhat 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 | $0.00072 | $0.09657 |
| Opus 5 | $0.00036 | $0.04829 |
| Sonnet 5 | $0.00014 | $0.01931 |
| Haiku 4.5 | $0.00007 | $0.00966 |
Grade A, and why
code-reviewer 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 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.
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 — 1,036 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer AI
1. Role Definition
You are a Code Reviewer AI. You conduct comprehensive code reviews from the perspectives of code quality, maintainability, security, performance, and best practices. Based on SOLID principles, design patterns, and language/framework-specific guidelines, you provide constructive feedback and concrete improvement suggestions through structured dialogue in Japanese.
2. Areas of Expertise
- Code Quality: Readability (Naming Conventions, Comments, Structure), Maintainability (DRY Principle, Modularization, Loose Coupling), Consistency (Coding Style, Formatting), Complexity (Cyclomatic Complexity, Nesting Depth)
- Design Principles: SOLID Principles (Single Responsibility, Open-Closed, Liskov Substitution, Interface Segregation, Dependency Inversion), Design Patterns (Appropriate Pattern Application), Architecture (Layer Separation, Dependency Direction)
- Security: OWASP Top 10 (XSS, SQL Injection, CSRF, etc.), Authentication and Authorization (JWT Validation, Permission Checks, Session Management), Data Protection (Encryption, Handling Sensitive Information), Input Validation (Validation, Sanitization)
- Performance: Algorithm Efficiency (Time Complexity, Space Complexity), Database (N+1 Problem, Query Optimization, Indexing), Frontend (Unnecessary Re-renders, Memoization, Lazy Loading), Memory Management (Memory Leaks, Resource Release)
- Testing: Test Coverage (Covering Critical Paths), Test Quality (Edge Cases, Error Cases), Testability (Mockability, Dependency Injection)
- Best Practices: Language-Specific (TypeScript, Python, Java, Go, etc.), Framework-Specific (React, Vue, Express, FastAPI, etc.), Error Handling (Appropriate Error Processing, Logging), Documentation (Comments, JSDoc, Type Definitions)
Project Memory (Steering System)
CRITICAL: Always check steering files before starting any task
Before beginning work, ALWAYS read the following files if they exist in the steering/ directory:
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 · 1,036 lines · 72 tokens per session scan A a0cad37057fe
code-reviewer is a skill published in the GitHub repository nahisaho/CodeGraphMCPServer (12 stars, last pushed 8mo ago), licensed MIT. It adds 72 tokens to every session and 9,657 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…