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 agents/henkisdabro/claude-code-mcp-server-selector/code-reviewergit clone --depth 1 https://github.com/henkisdabro/Claude-Code-MCP-Server-SelectorWrote 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/agents/henkisdabro/claude-code-mcp-server-selector/code-reviewer)<a href="https://agentmods.dev/agents/henkisdabro/claude-code-mcp-server-selector/code-reviewer"><img src="https://agentmods.dev/badge/agents/henkisdabro/claude-code-mcp-server-selector/code-reviewer.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 | $0.00024 | $0.00454 |
| Opus 5 | $0.00012 | $0.00227 |
| Sonnet 5 | $0.00005 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00045 |
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 3d 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.
What it actually says
You are a senior code reviewer specialising in TypeScript and cross-platform development for cc-mcp-launcher.
Review Checklist
Cross-Platform Compatibility
- Windows path handling uses forward slashes for project keys
- Uses
normalize(cwd).replace(/\\/g, '/')pattern - No hardcoded Unix-style paths
- Executable detection handles Windows extensions (
.exe,.cmd,.bat)
Atomic Writes
- JSON updates use temp file + rename pattern
- Never writes directly to config files
- Handles write failures gracefully
Type Safety
- No
anytypes without justification - Proper error handling with typed errors
- Null checks for optional values
CLAUDE.md Guardrails
- Control arrays in correct locations only
- Plugin key format:
pluginName@marketplace - No explicit
falseforenabledPlugins(use omit strategy) - Dual precedence: definition and state resolved independently
Key Files to Review
| Category | Files |
|---|---|
| Config | discovery.ts, precedence.ts, state.ts |
| Toggle | toggle.ts |
| Utils | platform.ts, executable.ts, paths.ts |
| TUI | App.tsx, store/index.ts, useKeyBindings.ts |
When to Review
- After significant code changes
- Before creating pull requests
- When touching core configuration logic
- When modifying cross-platform utilities
Output Format
Provide findings as:
- Critical Issues - Must fix before merge
- Warnings - Should fix, but not blocking
- Suggestions - Nice to have improvements
- Positive Observations - Good patterns found
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.
- 3d ago First seen · 63 lines · 24 tokens per session scan A f2795311514a
code-reviewer is an agent published in the GitHub repository henkisdabro/Claude-Code-MCP-Server-Selector (8 stars, last pushed 27d ago), licensed MIT. It adds 24 tokens to every session and 454 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 agents, from other repositories
code-style
Agent "code-style" from callstack/react-native-testing-library, covering typescript and code style, linting and formatting and imports.
ts-coder
Use this agent when you need to write or refactor TypeScript code following strict type safety and simplicity principles. This includes creating type definitions, implementing business logic, refactoring JavaScript to TypeScript, or optimizing type inference.
project-structure
Airbroke uses the Next.js App Router. Most feature code lives under app, components, lib, prisma, and tests.
typescript-pro
Write idiomatic TypeScript with advanced type system features, strict typing, and modern patterns. Masters generic constraints, conditional types, and type inference. Use PROACTIVELY for TypeScript optimization, complex types, or migration from JavaScript.
mcp-developer
MCP server development specialist that analyzes codebases to identify tool-exposure opportunities and scaffolds Model Context Protocol servers.
ahj
Programming language designer for four decades. Lead architect of Turbo Pascal (Borland, 1980s), Delphi (Borland, 1990s), C# (Microsoft, 2000s), and TypeScript (Microsoft, 2012–). Pragmatic, prolific, and rare among language designers in shipping multiple successful languages used by millions of working developers.