Agent skill

Claudraband

by halfwhey in halfwhey/claudraband

Use claudraband CLI to control Claude Code sessions programmatically.

MITAuto-check passed

Install Claudraband

skills CLI
$ npx skills add halfwhey/claudraband --skill claudraband -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install halfwhey/claudraband claudraband --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/halfwhey/claudraband.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills .claude/skills/claudraband && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
claudraband
GitHub stars
287
Token cost
~1.4k tokens
SKILL.md length
520 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Use claudraband CLI to control Claude Code sessions programmatically.

  • Automating Claude Code via the claudraband CLI — sending prompts
  • SKILL.md covers Commands, Flags, Session lifecycle and Permission prompts, plus 3 more sections
  • Calls node, bun and npx
  • Listing/resuming sessions

What it does

Claudraband is an agent skill from halfwhey/claudraband. Use claudraband CLI to control Claude Code sessions programmatically. Use when running, scripting, or automating Claude Code via the claudraband CLI — sending prompts, listing/resuming sessions, or working in interactive REPL mode. Triggers on any mention of claudraband, claudraband-cli, npx claudraband, bunx claudraband, or automating Claude Code sessions. Used when you need to ask yourself (Claude) a question

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with Bun and tmux. The repository describes itself as: Claude Code for the Power User. The licence is MIT.

When your agent uses it

  • Automating Claude Code via the claudraband CLI — sending prompts
  • Listing/resuming sessions
  • Working in interactive REPL mode
  • Any mention of claudraband

Example prompts

  • “/claudraband”

Requirements

  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit d2b6a7d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node
    • bun
    • npx
    • bunx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx and bunx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Claudraband loads about 1.4k tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 520 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~107
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from halfwhey/claudraband at commit d2b6a7d, republished under its MIT licence (© halfwhey). 520 words, ~1,428 tokens.

Download SKILL.mdSave it as .claude/skills/claudraband/SKILL.md (or your agent's skills folder).
name
claudraband
description
Use claudraband CLI to control Claude Code sessions programmatically. Use when running, scripting, or automating Claude Code via the claudraband CLI — sending prompts, listing/resuming sessions, or working in interactive REPL mode. Triggers on any mention of claudraband, claudraband-cli, npx claudraband, bunx claudraband, or automating Claude Code sessions. Used when you need to ask yourself (Claude) a question

Claudraband CLI

Claudraband spawns Claude Code in a hidden shared tmux session, tails its JSONL log, and provides a clean command-line interface for sending prompts, streaming output, and managing sessions.

Local built binary: node packages/claudraband-cli/dist/bin.js or bun packages/claudraband-cli/dist/bin.js

Published binary: claudraband via npx @halfwhey/claudraband or bunx @halfwhey/claudraband


Commands

Send a prompt
bash
node packages/claudraband-cli/dist/bin.js "your prompt here"

Positional args after flags are concatenated as the prompt. Blocks until Claude finishes all tool calls, then exits.

Interactive REPL
bash
node packages/claudraband-cli/dist/bin.js -i

Starts a read-eval-print loop. Send multiple prompts to the same session without restarting. Exit with Ctrl+D, cancel current prompt with Ctrl+C.

List sessions
bash
node packages/claudraband-cli/dist/bin.js sessions [--cwd <dir>]

Lists resumable sessions for a directory (defaults to cwd). Output per line: <sessionId> <date> <title>.

Sessions are stored at ~/.claude/projects/<encoded-cwd>/<sessionId>.jsonl. A session only appears here if the file is >= 100 bytes.

Resume a session
bash
node packages/claudraband-cli/dist/bin.js resume <sessionId> [prompt...]

Resumes a previous session by UUID. Optionally send a new prompt immediately.


Flags

FlagShortDefaultDescription
--help-h-Show usage and exit
--interactive-ifalseREPL mode
--cwd <dir>-cwdWorking directory for session
--claude "<flags>"-c-Claude CLI launch flags, e.g. --model sonnet --effort high
--approve-all-falseAuto-select first permission option
--terminal-backend <backend>-autoauto, tmux, or xterm
--debug-falseDebug logging to stderr
Permission modes
  • default -- prompt user for each tool call
  • plan -- plan only, no file edits
  • auto -- bypass all permission checks
  • acceptEdits -- auto-accept file edits
  • dontAsk -- skip all confirmations
  • bypassPermissions -- dangerously skip everything

Session lifecycle

tmux-backed sessions share a tmux session named claudraband-working-session. Each Claude session gets its own tmux window named with the Claude session ID, and the CLI sends prompts into that window's pane while tailing the JSONL log for events.

Turn completion: detected via 3-second idle timeout after Claude sends a response with no outstanding tool calls. This is not a hard delay -- the idle timer only starts after a response arrives.

Interruption:

  • Ctrl+C while prompt is running -- sends interrupt to Claude, waits for it to finish
  • Ctrl+C while idle -- stops session and exits
  • Ctrl+D in REPL -- exits the loop and stops the session

Show full SKILL.md (190 more words)Show less

Permission prompts

When Claude requests a tool permission, the CLI prints:

Permission: <title>
  <description>
  1. <option> (<kind>)
  2. <option> (<kind>)

With --approve-all, the first option is selected automatically and prints -> auto: <option name>.

If stdin is not a TTY and --approve-all is not set, permission is denied automatically.

Tool kinds shown in prompts: read, edit, execute, search, fetch, think, other.


Output

Events stream to stdout with ANSI color:

  • Grey -- assistant text
  • Bold yellow -- tool call: > ToolName
  • Green -- tool result: + ToolName
  • Red -- error: ! message
  • Dimmed -- thinking blocks and system messages

Use --debug to send diagnostic logs to stderr without polluting stdout.


Common examples

bash
# One-shot prompt
node packages/claudraband-cli/dist/bin.js "summarize the last 5 commits"

# Interactive with opus
node packages/claudraband-cli/dist/bin.js -i --claude "--model opus"

# Auto-approve all permissions
node packages/claudraband-cli/dist/bin.js --approve-all --claude "--permission-mode auto" "run tests and fix failures"

# Resume a session and continue
node packages/claudraband-cli/dist/bin.js sessions
node packages/claudraband-cli/dist/bin.js resume 550e8400-e29b-41d4-a716-446655440000 "implement what you planned"

# Different working directory
node packages/claudraband-cli/dist/bin.js --cwd /path/to/repo "what does this do?"

# Debug mode to trace events
node packages/claudraband-cli/dist/bin.js --debug "write a function" 2>debug.log

Gotchas

  • No prompt and no -i -- exits immediately with an error. Always provide one or the other.
  • Session not in sessions list -- file may be < 100 bytes (e.g. aborted immediately). Check ~/.claude/projects/ directly.
  • --claude "--permission-mode ..." change mid-session -- requires restarting the session (Claude Code reloads on mode change). Don't change it after the first prompt if you need consistency.
  • --terminal-backend xterm -- fallback for environments without tmux. Slightly less reliable for long sessions; prefer tmux or auto.
  • --approve-all with non-TTY stdin -- --approve-all takes precedence. Without it, all permissions are denied when stdin is not a TTY (e.g. piped input).

© halfwhey, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills of halfwhey/claudraband.

Open the folder on GitHubat commit d2b6a7d

Compare with similar skills

Claudraband next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Claudraband compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Claudraband this skillhalfwhey/claudraband287—~1.4kAutomated safety check: PassMIT
1passwordtrpc-group/trpc-agent-go1.9k14 repos~656Automated safety check: PassApache-2.0
CodeGraph Agent Evalcolbymchenry/codegraph74k—~950Automated safety check: PassMIT
Tmuxtrpc-group/trpc-agent-go1.9k23 repos~868Automated safety check: PassApache-2.0
OpenTUI Terminal Interfacescline/cline70k—~1.9kAutomated safety check: PassApache-2.0
CodexBar Live QAsteipete/CodexBar22k—~1.2kAutomated safety check: PassMIT

Similar skills

  • 1password

    trpc-group/trpc-agent-go

    Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.

    1.9k GitHub starsUsed in 14 repos~656 tokens
    AI & LLM EngineeringAuto-check passed
  • CodeGraph Agent Eval

    colbymchenry/codegraph

    Benchmarks how much CodeGraph helps a coding agent on a real repository, comparing runs with and without it for a chosen local or published version.

    74k GitHub stars~950 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Tmux

    trpc-group/trpc-agent-go

    Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

    1.9k GitHub starsUsed in 23 repos~868 tokens
    Data & AnalyticsAuto-check passed
  • Helps build terminal user interfaces with OpenTUI using its core imperative API or its React and Solid reconcilers, with references for layout, keyboard, animation and testing.

    70k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed
  • CodexBar Live QA

    steipete/CodexBar

    Runs live QA for the CodexBar app: provider usage matrix checks through its packaged CLI, config validation and menu checks, with 1Password-backed credentials handled safely.

    22k GitHub stars~1.2k tokensUpdated today
    Testing & QAAuto-check passed
  • Tmux

    openclaw/openclaw

    Control tmux sessions/panes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.

    392k GitHub starsUsed in 1 repo~640 tokens
    Auto-check passed

More from halfwhey/claudraband

  • Claudraband

    halfwhey/claudraband

    Use claudraband CLI and daemon workflows programmatically to send prompts, resume sessions, inspect status, and manage live session state.

    287 GitHub stars~947 tokensUpdated 5 mo ago
    Auto-check passed

Works with

Questions about Claudraband

What does Claudraband do?

Use claudraband CLI to control Claude Code sessions programmatically. Claudraband is an agent skill from halfwhey/claudraband. Use claudraband CLI to control Claude Code sessions programmatically.

When should I use Claudraband?

Claudraband fits situations like: automating Claude Code via the claudraband CLI — sending prompts; listing/resuming sessions; working in interactive REPL mode; any mention of claudraband.

How do I install Claudraband in Claude Code?

Run `npx skills add halfwhey/claudraband --skill claudraband -a claude-code`. Or copy the skill folder (skills in halfwhey/claudraband) into .claude/skills/claudraband in your project. Claude Code loads it when a task matches its description.

How do I install Claudraband in Codex?

Run `npx skills add halfwhey/claudraband --skill claudraband -a codex`. Or copy the skill folder (skills in halfwhey/claudraband) into .agents/skills/claudraband in your project. Codex loads it when a task matches its description.

Can I use Claudraband in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add halfwhey/claudraband --skill claudraband -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/claudraband, .gemini/skills/claudraband, .github/skills/claudraband and .opencode/skills/claudraband in your project.

What does Claudraband need to run?

Going by SKILL.md and its folder, Claudraband needs the command-line tools its instructions call (node, bun, npx and bunx). Our summary lists: Node.js.

Does Claudraband access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Claudraband safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Claudraband use?

Claudraband is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Claudraband use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Claudraband?

Skills that share tags, products or a category with Claudraband: 1password (trpc-group/trpc-agent-go, 1.9k stars), CodeGraph Agent Eval (colbymchenry/codegraph, 74k stars), Tmux (trpc-group/trpc-agent-go, 1.9k stars) and OpenTUI Terminal Interfaces (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Claudraband?

halfwhey (a GitHub user) maintains it in halfwhey/claudraband, which has 287 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on April 18, 2026.

Source: halfwhey/claudraband on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.