claw-shell

claw-shell is a skill for Claude Code, Codex from CUHK-AIM-Group/NeuroClaw. It costs 136 tokens per session (1,328 once invoked), scanned D, original, MIT.

A central shell-execution skill for NeuroClaw, used to run commands in a dedicated tmux session. It captures command output and applies confirmation checks to dangerous operations.

In plain words
What is it for?
Running commands such as FreeSurfer processing, dependency setup, Git and Conda operations, file inspection, and other shell tasks required by NeuroClaw.
Why use it?
Long-running or system-level commands can be hard to monitor safely from a normal terminal. A dedicated session keeps them running and provides a controlled place to inspect their output.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Running commands such as FreeSurfer processing, dependency setup, Git and Conda operations, file inspection, and other shell tasks required by NeuroClaw.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cuhk-aim-group/neuroclaw/claw-shell
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.

Any agent
npx skills add CUHK-AIM-Group/NeuroClaw --skill claw-shell
Clone the repo
git clone --depth 1 https://github.com/CUHK-AIM-Group/NeuroClaw

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 claw-shell

README.md
[![agentmods](https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/claw-shell/github.svg)](https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/claw-shell)
Your own site
<a href="https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/claw-shell"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/claw-shell/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.

agentmods 80×15 button for claw-shell

Your own site · 80×15
<a href="https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/claw-shell"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/claw-shell.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,328 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00136 $0.01328
Opus 5 $0.00068 $0.00664
Sonnet 5 $0.00027 $0.00266
Haiku 4.5 $0.00014 $0.00133

Measured 9d ago against content hash d8d7413406b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade D, and why

claw-shell scanned grade D 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (handler.js), 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.

| Dangerous (requires confirmation) | `rm -rf ...`, `sudo apt install ...`, `docker system prune -a` | Asks user “YES” before proceeding |

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| Dangerous (requires confirmation) | `rm -rf ...`, `sudo apt install ...`, `docker system prune -a` | Asks user “YES” before proceeding |
skills/claw-shell/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claw Shell

Overview

claw-shell is the central, safe shell execution layer for the entire NeuroClaw system. All long-running or system-level commands (FreeSurfer recon-all, dependency installation steps, git operations, conda commands, file operations, etc.) are routed through this skill.

Core principles:

  • Always uses the dedicated tmux session named claw (creates it automatically if missing).
  • Never touches any other tmux session or runs commands directly in the main shell.
  • Captures the latest pane output and returns it to the calling skill/agent.
  • Enforces strict safety rules: dangerous commands (sudo, rm, reboot, etc.) trigger an explicit user confirmation step before execution.

This design solves the problems of the main agent not proactively installing dependencies and handling long-running commands, as identified in the MedicalClaw evaluation, by providing centralized logging, detachment support, and safe execution.

Quick Reference

Type Example Commands Behavior
Safe (direct run) ls -la, cat log.txt, git status Executes immediately in claw session
Environment setup source $FREESURFER_HOME/SetUpFreeSurfer.sh Executes and returns output
Long-running pipeline recon-all -subjid sub-001 -all -parallel Runs in background-capable tmux pane
Dangerous (requires confirmation) rm -rf ..., sudo apt install ..., docker system prune -a Asks user “YES” before proceeding

Tool Interface
Tool name: claw_shell_run
Input:

  • command (string, required): the full shell command to run inside the claw tmux session.

Installation

This is a core NeuroClaw skill and requires no external packages beyond tmux.

One-time setup (run once via dependency-planner or manually):

Read the full file on GitHub · 130 lines

Files

What ships with it

1 file 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. 9d ago First seen · 130 lines · 136 tokens per session scan D d8d7413406b9

Subscribe to this mod's changes

claw-shell is a skill published in the GitHub repository CUHK-AIM-Group/NeuroClaw (83 stars, last pushed 2d ago), licensed MIT. It adds 136 tokens to every session and 1,328 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens