What is claude-code-boost CLAUDE.md?

Project guidance for Claude Code Boost, a TypeScript command-line tool that reviews Claude Code actions and automatically approves clearly safe ones. It also describes the project structure, commands, tests, and security approach.

Use it when developing, testing, or reviewing Claude Code Boost, especially its command-line entry point, action-approval logic, hook communication, validation, and security rules.

It gives a coding agent the context needed to work in the repository without guessing where code belongs or how changes should be built and checked.

claude-code-boost CLAUDE.md — Instructions file for coding agents by yifanzz: Project guidance for Claude Code Boost, a TypeScript command-l

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 instructions/yifanzz/claude-code-boost/claude-md

Clone the repo

git clone --depth 1 https://github.com/yifanzz/claude-code-boost

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/yifanzz/claude-code-boost/claude-md.svg)](https://agentmods.dev/instructions/yifanzz/claude-code-boost/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/yifanzz/claude-code-boost/claude-md"><img src="https://agentmods.dev/badge/instructions/yifanzz/claude-code-boost/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,467 This file is loaded in full into every session.

When invoked 2,467 The same file — it is already loaded in full.

Security scan D 2 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.

Model	Per session	Once invoked
Fable 5	$0.02467	$0.02467
Opus 5	$0.01234	$0.01234
Sonnet 5	$0.00493	$0.00493
Haiku 4.5	$0.00247	$0.00247

Measured 4d ago against content hash a5ba0ff8169c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

claude-code-boost CLAUDE.md scanned grade D with 2 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `--user`: Install to user settings (`~/.claude/settings.json`)

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Destructive-only blocking** - Only blocks genuinely harmful operations (rm -rf /, system wipes)

CLAUDE.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Claude Code Boost is a TypeScript-based CLI tool that provides intelligent auto-approval hooks for Claude Code. It enhances developer productivity by automatically approving safe development operations while blocking genuinely destructive commands.

Architecture

The project follows a simple CLI architecture:

Entry Point: src/index.ts - Uses Commander.js for CLI structure
Main Command: src/commands/auto-approve-tools.ts - Core logic for tool approval decisions
Hook Integration: Processes Claude Code PreToolUse hooks via stdin/stdout JSON communication
AI-Powered Decisions: Falls back to Claude API for complex approval decisions
Type Safety: src/types/hook-schemas.ts - Zod schemas for input/output validation
Security Model: Two-tier approval system:
- Fast approval for unambiguously safe tools (Read, LS, Glob, etc.)
- AI-powered analysis for complex operations using prompts/system-prompt.md

Development Commands

Build and Test

npm run build          # TypeScript compilation to dist/
npm run type-check     # Type checking without compilation
npm run test           # Run test suite with Vitest
npm run test:watch     # Watch mode for tests
npm run test:env       # Run tests with .env.local file

Linting and Formatting

npm run lint           # ESLint checking
npm run lint:fix       # Auto-fix linting issues
npm run prettier       # Format code with Prettier
npm run prettier:check # Check code formatting

Development

npm run dev            # Run CLI with tsx (development mode)
npm run prepublishOnly # Full build + test + lint pipeline

CLI Testing

# Test the CLI locally (requires ANTHROPIC_API_KEY env var or config.json)
echo '{"session_id":"test","transcript_path":"/tmp/test","tool_name":"Read","tool_input":{"file_path":"/test"}}' | ANTHROPIC_API_KEY=your_key npm run dev auto-approve-tools

# Test with API authentication
echo '{"session_id":"test","transcript_path":"/tmp/test","tool_name":"Read","tool_input":{"file_path":"/test"}}' | npm run dev auto-approve-tools

# Install CCB hook to Claude Code settings
npm run build && node dist/index.js install --user        # Install to user settings
npm run build && node dist/index.js install --project     # Install to project settings
npm run build && node dist/index.js install --project-local # Install to project local settings

Read the full file on GitHub · 263 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.

4d ago First seen · 263 lines · 2,467 tokens per session scan D a5ba0ff8169c

Subscribe to this mod's changes

claude-code-boost CLAUDE.md is an instructions file published in the GitHub repository yifanzz/claude-code-boost (165 stars, last pushed 5mo ago), licensed MIT. It adds 2,467 tokens to every session, about $0.0123 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

claude-code-boost CLAUDE.md