Shell Builtins logo

Shell Builtins

OrganizationPopular
charmbracelet
shell-builtins

Use when creating a new shell builtin command for Crush (internal/shell/), editing an existing one, or when the user needs to understand how commands are intercepted in Crush's embedded shell.

Overview

Publishercharmbracelet
Repositorycrush
Skill nameshell-builtins
Stars
28.6K
Forks
2.3K
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by charmbracelet on GitHub. Read the source before you install it.

Installation

Install the Shell Builtins AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/charmbracelet/crush/tree/main/.agents/skills/shell-builtins
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/charmbracelet/crush.git /tmp/crush
mkdir -p .claude/skills
cp -r /tmp/crush/.agents/skills/shell-builtins .claude/skills/shell-builtins
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Shell Builtins in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Shell Builtins on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Shell Builtins is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Shell Builtins

Crush's shell (internal/shell/) uses mvdan.cc/sh/v3 for POSIX shell emulation. Commands can be intercepted before they reach the OS by adding builtins — functions handled in-process.

How Builtins Work

Builtins live in builtinHandler() in internal/shell/run.go. This is an interp.ExecHandlerFunc middleware registered in standardHandlers() before the block handler, so builtins run even for commands that would otherwise be blocked. The same handler chain is shared by the stateful Shell type and the stateless Run entrypoint used by the hook runner, so builtins are available identically in the bash tool and in hooks.

The handler is a switch on args[0]. Each case either handles the command inline or delegates to a helper function.

Adding a New Builtin

  1. Add the case to the switch in builtinHandler() in run.go.
  2. Get I/O from the handler context, not from os.Stdin/os.Stdout. This ensures the builtin works with pipes and redirections:
    go
    case "mycommand":
        hc := interp.HandlerCtx(ctx)
        return handleMyCommand(ctx, args, hc.Stdin, hc.Stdout, hc.Stderr)
  3. Implement the handler in its own file (e.g., internal/shell/mycommand.go). The function signature must accept a context.Context as the first parameter, plus args, stdin, stdout, and stderr:
    go
    func handleMyCommand(ctx context.Context, args []string, stdin io.Reader, stdout, stderr io.Writer) error {
        // args[0] is the command name ("mycommand"), args[1:] are arguments.
        // Write output to stdout, errors to stderr.
        // Return nil on success, or interp.ExitStatus(n) for non-zero exit codes.
    }
  4. Poll ctx in every unbounded loop. Builtins that iterate over input, emit values in a generator-style loop, or do any other work that can exceed a few milliseconds MUST check ctx.Err() on each iteration and return it verbatim when non-nil. Hook timeouts rely on this: an unbounded builtin that never polls ctx cannot be interrupted by a hook's timeout_sec, and the hook runner will have to abandon the goroutine (see internal/hooks/runner.go). Returning ctx.Err() (not interp.ExitStatus(n)) lets callers distinguish "command exited non-zero" from "we ran out of time".
    go
    for _, item := range items {
        if err := ctx.Err(); err != nil {
            return err
        }
        // ... process item
    }
  5. Return values: return nil for success, interp.ExitStatus(n) for non-zero exit codes, or ctx.Err() on cancellation. Write error messages to stderr before returning.
  6. No extra wiring needed — builtinHandler() is already registered in standardHandlers().

Existing Builtins

CommandFileDescription
jqjq.goJSON processor using github.com/itchyny/gojq

Frequently asked questions

What does the Shell Builtins AI skill do?

Use when creating a new shell builtin command for Crush (internal/shell/), editing an existing one, or when the user needs to understand how commands are intercepted in Crush's embedded shell.

Why use Shell Builtins on TypingMind?

Because you install it once and use it with any model. Shell Builtins is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Shell Builtins in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/charmbracelet/crush/tree/main/.agents/skills/shell-builtins. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Shell Builtins?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Shell Builtins?

As many as you like. As long as a model supports skills, you can use Shell Builtins with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Shell Builtins AI skill free?

It is published on GitHub by charmbracelet. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇