crow-batch-workspace

crow-batch-workspace is a skill for Claude Code, Codex from corveil/crow. It costs 59 tokens per session (2,631 once invoked), scanned B, original, Apache-2.0.

A setup helper for creating several Crow workspaces at the same time. It can also create separate exploration workspaces from ticket URLs.

In plain words
What is it for?
Use it when you need multiple workspaces for separate tasks or tickets, including exploration sessions that should not use the normal feature branch.
Why use it?
Setting up workspaces one by one takes longer. Running their setup tasks together reduces the total waiting time.

Skill for Claude CodeCodex

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 skills/corveil/crow/crow-batch-workspace
Any agent
npx skills add corveil/crow --skill crow-batch-workspace
Clone the repo
git clone --depth 1 https://github.com/corveil/crow

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,631 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00059 $0.02631
Opus 5 $0.00030 $0.01316
Sonnet 5 $0.00012 $0.00526
Haiku 4.5 $0.00006 $0.00263

Measured 3d ago against content hash c98cfde2db17, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

crow-batch-workspace scanned grade B with 1 finding 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 3d 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.

1. **Read config**: `cat {devRoot}/.claude/config.json`
skills/crow-batch-workspace/SKILL.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crow Batch Workspace Setup Skill

Purpose

Sets up multiple crow workspaces in parallel, dramatically reducing total setup time. Delegates to the existing /crow-workspace skill's setup.sh for each workspace but fires all executions simultaneously.

Important: Sandbox Bypass

All crow, gh, glab, and git worktree commands require dangerouslyDisableSandbox: true because they communicate via Unix socket, need network/TLS access, or write outside the sandbox-allowed directories.

Activation

This skill activates when:

  • User invokes /crow-batch-workspace command
  • User invokes /crow-batch-workspace --explore <url> <url> … (CROW-1149)
  • User asks to "set up multiple workspaces", "batch workspace setup", or provides multiple ticket URLs at once

Explore mode (--explore)

When the invocation includes --explore, every workspace in the batch is an exploration session: use /crow-workspace's Explore Prompt Template, pass --explore to each setup.sh, and name worktrees/branches/sessions with -explore- so a later Start Working on the same ticket is free to take the normal feature branch. Do not attach to existing PRs. See /crow-workspace Explore mode for the full contract.

Concurrency Safety

The crow CLI is safe for concurrent use. Multiple crow commands can run simultaneously without race conditions:

  • Socket Server: Each CLI connection is dispatched to GCD's global concurrent queue. Multiple connections are accepted and processed in parallel.
  • State Mutations: All RPC handlers use await MainActor.run { ... }, serializing all AppState mutations on the main thread.
  • Persistence: JSONStore uses NSLock to serialize disk writes. Concurrent mutate() calls are safe.
  • Git Operations: Each setup.sh creates its own worktree at a unique path, its own session (unique UUID), and its own terminal. There are no shared resources between parallel workspace setups.

Autonomous Execution

This skill runs autonomously without permission prompts because:

  1. All crow, gh, glab, and git commands are pre-approved in {devRoot}/.claude/settings.local.json
  2. All commands use dangerouslyDisableSandbox: true (sandbox excludes these binaries)
  3. setup.sh is pre-approved via Bash(bash .claude/skills/crow-workspace/setup.sh *)

Read the full file on GitHub · 245 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. 3d ago First seen · 245 lines · 59 tokens per session scan B c98cfde2db17

Subscribe to this mod's changes

crow-batch-workspace is a skill published in the GitHub repository corveil/crow (18 stars, last pushed 3d ago), licensed Apache-2.0. It adds 59 tokens to every session and 2,631 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

orchestrate-monitor

/orchestrate のワーカー監視レシピ(capture 解析・状態判定・介入判断・完了検証)を、bash 3.2 互換の実行可能スクリプトと fixture ベーステストとして資産化したもの。並列ワーカーを監督するときに使う。.

Kewton/CommandMate · 78 tokens

demo-video

CommandMate の 30 秒デモ動画(日本語版・英語版)を隔離環境で全自動生成する。絵コンテ駆動のシーン録画・テロップ焼き込み・ffmpeg 合成・尺検証まで。「デモ動画」「demo video」「デモを録画」等の指示で使う。.

Kewton/CommandMate · 84 tokens

catalog-reconcile

組み込みスラッシュコマンドのカタログを各 CLI の権威ソースへリコンサイルする(--check で規模把握 → --write → 人手レビュー → attestation の採り直し → 検証).

Kewton/CommandMate · 62 tokens

cmate-verify

リポジトリの検証ゲート(lint / typecheck / test / build 等)を .commandmate/verify.yaml に宣言し、worktree の cwd で逐次実行して exit code で合否を判定する。verify.yaml が無いリポジトリでは CI 定義から起案する。作業完了を主張する前の検証や、並列ワーカーの完了判定に使う。.

Kewton/CommandMate · 106 tokens

release

Skill "release" from Kewton/CommandMate, covering リリーススキル, 使用方法, 前提条件, 全体の流れ and この手順が「なぜこの形か」.

Kewton/CommandMate · 36 tokens

video-to-gif

録画済みの mp4 / webm / mov を、GitHub の markdown ビューアが実際に再生できる GIF に変換する。バイト予算を指定すると解像度・fps・パレットを段階的に落として収まるまで再試行し、収まらなければ書かずに落ちる。「GIF を作って」「GIF 化」「mp4 を GIF に」「README に貼れる動画」等の指示で使う。.

Kewton/CommandMate · 113 tokens