crow-workspace

crow-workspace is a skill for Claude Code, Codex from corveil/crow. It costs 75 tokens per session (8,269 once invoked), scanned C, original, Apache-2.0.

A skill for setting up a Crow work session, including a Git worktree, a Crow session, an automatically launched Claude Code process, and ticket details. A Git worktree is a separate working directory connected to the same repository.

In plain words
What is it for?
Use it when starting work on a Crow ticket, creating an implementation or exploration workspace, or configuring sessions for different organizations and Git providers.
Why use it?
It prepares the workspace and session information needed to start work on a Crow ticket without setting up each part manually.

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

Made for: Claude Code, Codex.

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.

agentmods badge for crow-workspace

README.md
[![agentmods](https://agentmods.dev/badge/skills/corveil/crow/crow-workspace.svg)](https://agentmods.dev/skills/corveil/crow/crow-workspace)
Your own site
<a href="https://agentmods.dev/skills/corveil/crow/crow-workspace"><img src="https://agentmods.dev/badge/skills/corveil/crow/crow-workspace.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,269 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 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.

ModelPer sessionOnce invoked
Fable 5 $0.00075 $0.08269
Opus 5 $0.00037 $0.04134
Sonnet 5 $0.00015 $0.01654
Haiku 4.5 $0.00007 $0.00827

Measured 4d ago against content hash a07c25603fae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

crow-workspace scanned grade C 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.

The scan reads SKILL.md. This mod also ships 5 executable files (setup_binary_test.sh, setup_gateway_test.sh, setup_hook_test.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

Backward-compatible: with no `sessionEnv` map and no `--session-env` flag, `setup.sh` writes no `.env` block beyond what attribution/gateway already require. The file is `chmod 600` and stays in the worktree's git exclud

Reads agent configuration directoriesmediumAgent snooping

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

cat > {devRoot}/.claude/prompts/crow-prompt-{session_name}.md << 'PROMPT'
skills/crow-workspace/SKILL.md · 724 lines

How it starts

The opening of the file, as written. The whole thing — 724 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crow Workspace Setup Skill

Purpose

Orchestrates work sessions in Crow by setting up git worktrees and creating a crow session with auto-launched Claude Code and ticket metadata. Supports multiple organizations/workspaces with different Git providers.

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-workspace command
  • User invokes /crow-workspace --explore <url> (exploration / bootstrap-only session)
  • User asks to "set up crow workspace" or "start working on" a feature in Crow
  • User asks to "start exploring" a ticket in Crow

Explore mode (--explore)

When the invocation includes --explore (the board's Start Exploring, crow explore-issue, or a crow:explore auto-pickup), run the same worktree / session / terminal setup as a normal workspace, but:

  1. Seed prompt — use the Explore Prompt Template below, not the implement/build First Prompt Template. The agent maps and explains the ticket area and stops. No edits, no commits, no push, no PR.
  2. Pass --explore to setup.sh — that stamps the session isExplore (the board/sidebar "Exploring" badge) and skips auto-assign + In Progress board transitions. Exploring is not claiming the ticket as work.
  3. Distinct worktree/branch/session names so a later Start Working on the same ticket can still create the normal feature branch:
    • Worktree: {devRoot}/{workspace}/{repo}-{ticket_number}-explore-{brief_slug}
    • Branch: feature/{repo}-{ticket_number}-explore-{brief_slug}
    • Session name: {repo}-{ticket_number}-explore-{slug}
  4. Do not attach to an existing PR's branch. If a PR already exists, mention it in the prompt as context only. A throwaway explore branch from {base_branch} keeps the real PR branch free for a later work session.
  5. Do not pass --pr-number / --pr-url / --pr-branch to setup.sh in explore mode.

Read the full file on GitHub · 724 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 724 lines · 75 tokens per session scan C a07c25603fae

Subscribe to this mod's changes

crow-workspace is a skill published in the GitHub repository corveil/crow (18 stars, last pushed 4d ago), licensed Apache-2.0. It adds 75 tokens to every session and 8,269 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, 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

linear-tickets

Use Orca's Linear CLI through orca linear ... commands to read linked ticket context with orca linear issue --current --full --json, post completion updates, move work forward through Linear workflow states, attach PR/MR links with orca linear attach --current --url --title "PR/MR link" --json, and triage Linear tasks…

stablyai/orca · 160 tokens

orca-linear

Use Orca's Linear CLI through orca linear ... commands to read linked ticket context with orca linear issue --current --full --json, post completion updates, move work forward through Linear workflow states, attach PR/MR links with orca linear attach --current --url --title "PR/MR link" --json, and triage Linear tasks…

stablyai/orca · 145 tokens

factory-mcp

Use the Warp Factory MCP to hand work to a software factory and collaborate with it — bundle local work and send it to the cloud, find factory tasks from a Slack thread / Linear ticket / description, and pull a task down to test or iterate locally and hand it back.

warpdotdev/warp · 58 tokens

backlog

Read, work, and maintain a repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being…

umputun/agterm · 95 tokens

triage-issues

Review and assess every issue in the TMDb project board's Backlog column — re-verify each against current main with a read-only fan-out, close the mechanically dead, promote the actionable to Ready with priority, size and execution order, and leave the rest in Backlog naming the decision they need. Use to groom the…

adamayoung/TMDb · 95 tokens

plan

Epic decomposition into trackable, right-sized tasks. Three modes — audit-aware (codebase-audit reports), workflow-audit-aware (handoff.yaml with pre-rated findings), standalone (from scratch). Light convention scanning for projects without CLAUDE.md.

Terryc21/workflow-audit · 53 tokens