shell

shell is a skill for Claude Code from zylos-ai/zylos-core. It costs 23 tokens per session (221 once invoked), scanned A, original, MIT.

A communication channel that connects the zylos shell's interactive command-line session to Claude. It sends user input through a local Unix socket and returns Claude's responses to the shell.

In plain words
What is it for?
Use it to connect a zylos shell REPL to Claude, deliver shell input to the agent, and display the agent's replies in the terminal.
Why use it?
It allows a terminal-based conversation with the agent without requiring the shell itself to implement the agent's response handling. The socket connection carries complete messages between the two processes.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it to connect a zylos shell REPL to Claude, deliver shell…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zylos-ai/zylos-core/shell
About the project

Zylos is open-source infrastructure that gives an AI agent persistent memory, scheduled activity, communication channels, and the ability to maintain and extend itself. Individuals and teams use it with Claude Code or Codex through Telegram, Lark, or a web console. Its catalogue add-ons define settings, instructions, and skills for operating the agent.

zylos-ai/zylos-core · 1,151 stars · on GitHub · zylos.ai

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 zylos-ai/zylos-core --skill shell
Clone the repo
git clone --depth 1 https://github.com/zylos-ai/zylos-core

Made for: Claude Code.

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 shell

README.md
[![agentmods](https://agentmods.dev/badge/skills/zylos-ai/zylos-core/shell.svg)](https://agentmods.dev/skills/zylos-ai/zylos-core/shell)
Your own site
<a href="https://agentmods.dev/skills/zylos-ai/zylos-core/shell"><img src="https://agentmods.dev/badge/skills/zylos-ai/zylos-core/shell.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 221 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00023 $0.00221
Opus 5 $0.00012 $0.00111
Sonnet 5 $0.00005 $0.00044
Haiku 4.5 $0.00002 $0.00022

Measured 7d ago against content hash cb519ea99536, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

shell scanned grade A with 0 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/send.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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/shell/SKILL.md · 24 lines

What it actually says

Shell Channel

Communication channel for zylos shell — the CLI interactive mode.

How It Works

  1. zylos shell starts a readline REPL and a Unix domain socket server
  2. User input is sent to Claude via c4-receive (channel=shell, endpoint=socket path)
  3. Claude responds via c4-send which invokes scripts/send.js
  4. send.js connects to the Unix socket and delivers the response to the REPL
  5. The REPL prints the response and prompts for the next input

Socket Protocol

  • Socket path is passed as the endpoint (e.g., /tmp/zylos-shell-<pid>.sock)
  • send.js connects, writes the full message as UTF-8, then closes the connection
  • The REPL reassembles the message from socket data events
Files

What ships with it

2 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. 7d ago First seen · 24 lines · 23 tokens per session scan A cb519ea99536

Subscribe to this mod's changes

shell is a skill published in the GitHub repository zylos-ai/zylos-core (1,151 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 221 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.