vercel-labs/bash-tool is a tool for AI agents that runs Bash commands and reads or writes files in a sandbox, with compatibility for the AI SDK. It gives agents a way to work with command-line operations and files. The catalogue entries are skills and instructions that extend agent use of this tool.
Borrowing it
Nothing to install: this file belongs to vercel-labs/bash-tool. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vercel-labs/bash-tool/main/CLAUDE.mdgit clone --depth 1 https://github.com/vercel-labs/bash-toolWrote 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/instructions/vercel-labs/bash-tool/claude-md)<a href="https://agentmods.dev/instructions/vercel-labs/bash-tool/claude-md"><img src="https://agentmods.dev/badge/instructions/vercel-labs/bash-tool/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/vercel-labs/bash-tool/claude-md"><img src="https://agentmods.dev/badge/instructions/vercel-labs/bash-tool/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00617 | $0.00617 |
| Opus 5.5 | $0.00247 | $0.00247 |
| Sonnet 5.5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
bash-tool CLAUDE.md 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 1mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance for Claude Code when working on this project.
Project Overview
bash-tool is a generic bash tool for AI agents, compatible with AI SDK (https://ai-sdk.dev/). It provides bash, readFile, and writeFile tools that work with a sandboxed environment.
Commands
pnpm build # Compile TypeScript to dist/
pnpm typecheck # Type check without emitting
pnpm test # Run tests in watch mode
pnpm test:run # Run tests once
pnpm lint # Check with Biome
pnpm lint:fix # Fix lint issues
pnpm knip # Check for unused exports/dependencies
pnpm validate # Run all checks (lint, knip, typecheck, test)
Architecture
Entry Point
src/index.ts- Public exports only (createBashTooland types)src/tool.ts- MaincreateBashTool()function that orchestrates everything
Core Interfaces (src/types.ts)
Sandbox- Abstract interface for sandbox implementations (executeCommand, readFile, writeFile, stop)CreateBashToolOptions- Configuration for createBashToolBashToolkit- Return type with tools and sandbox instance
Sandbox Adapters (src/sandbox/)
just-bash.ts- Default adapter using just-bash (optional peer dependency)vercel.ts- Adapter wrapping @vercel/sandbox instances
Tools (src/tools/)
bash.ts- Execute bash commands with contextual LLM instructionsread-file.ts- Read file contentswrite-file.ts- Write files
File Loading (src/files/)
loader.ts- Loads files from inline content or disk directories
Key Design Decisions
-
Optional peer dependencies: just-bash and @vercel/sandbox are optional. Dynamic imports with helpful error messages when not installed.
-
Destination directory: All files go to
destination(default:/workspace). This is also the working directory for commands. -
Contextual instructions: The bash tool generates LLM instructions that include the working directory and list of available files.
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.
- 1mo ago First seen · 63 lines · 617 tokens per session scan A 3f82094a42a3
bash-tool CLAUDE.md is an instructions file published in the GitHub repository vercel-labs/bash-tool (628 stars, last pushed 2mo ago), licensed MIT. It adds 617 tokens to every session, about $0.0025 per session on Opus 5.5. 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 instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.