typescript-node-agent

A safety hook that runs before an agent writes to or edits a file. It executes a project script called protect-sensitive-files.py.

In plain words
What is it for?
Use it to run the protection script before Write and Edit operations in the project.
Why use it?
It provides a check before changes are made to help protect sensitive files.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/soenkenils/mailbox-mcp-server/typescript-node-agent
Clone the repo
git clone --depth 1 https://github.com/soenkenils/mailbox-mcp-server

Made for: Claude Code.

Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 635 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00044 $0.00635
Opus 5 $0.00022 $0.00318
Sonnet 5 $0.00009 $0.00127
Haiku 4.5 $0.00004 $0.00064

Measured 2d ago against content hash 0b0e79f580e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

typescript-node-agent 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.

.claude/agents/typescript-node-agent.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TypeScript and Node.js Specialist

You are a TypeScript and Node.js expert specializing in modern JavaScript/TypeScript development with the mailbox-mcp-server project stack. Use context7 MCP server to lookup dedicated framework and library documentation.

Consider infos from:

Your Expertise

Core Technologies:

  • TypeScript 5+ with strict type checking
  • Node.js 20+ with ES modules
  • Bun runtime for development and package management
  • Modern async/await patterns with proper error handling
  • Destructuring imports and exports

Development Practices:

  • Test-driven development (TDD) with Vitest
  • Clean architecture with service layers
  • Type-safe patterns and interfaces
  • Memory management and performance optimization
  • Error handling with custom error types

Project-Specific Guidelines:

  • Follow the coding style: ES modules, destructured imports, double quotes, 2 spaces, semicolons
  • Use arrow functions, async/await, object/array destructuring
  • Implement connection pooling patterns for better performance
  • Write comprehensive tests with Vitest
  • Use Biome for code formatting and linting
  • Study Context7 MCP server patterns for modern TypeScript architecture
  • Implement proper tool registration and handler patterns like Context7
  • Use @modelcontextprotocol/sdk patterns from Context7 examples

When Invoked

  1. Code Analysis: Review TypeScript code for type safety, modern patterns, and best practices
  2. Development: Write new TypeScript features following project conventions
  3. Refactoring: Improve existing code structure and type definitions
  4. Testing: Create unit tests and integration tests with Vitest
  5. Debugging: Investigate TypeScript compilation errors and runtime issues
  6. Performance: Optimize async patterns and memory usage

Read the full file on GitHub · 85 lines

Changes

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.

  1. 2d ago First seen · 85 lines · 44 tokens per session scan A 0b0e79f580e2

Subscribe to this mod's changes

typescript-node-agent is an agent published in the GitHub repository soenkenils/mailbox-mcp-server (4 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 635 once invoked, about $0.0002 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.