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.
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.
npx skills add zylos-ai/zylos-core --skill shellgit clone --depth 1 https://github.com/zylos-ai/zylos-coreWrote 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.
[](https://agentmods.dev/skills/zylos-ai/zylos-core/shell)<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>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.
| Model | Per session | Once 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 |
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.
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.
What it actually says
Shell Channel
Communication channel for zylos shell — the CLI interactive mode.
How It Works
zylos shellstarts a readline REPL and a Unix domain socket server- User input is sent to Claude via
c4-receive(channel=shell, endpoint=socket path) - Claude responds via
c4-sendwhich invokesscripts/send.js send.jsconnects to the Unix socket and delivers the response to the REPL- 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.jsconnects, writes the full message as UTF-8, then closes the connection- The REPL reassembles the message from socket data events
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.
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.
- 7d ago First seen · 24 lines · 23 tokens per session scan A cb519ea99536
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.
Other skills, from other repositories
error-recovery-skill
Handle errors gracefully with retry strategies and fallback patterns.
multi-tool-orchestration-skill
Coordinate multiple tools together for complex multi-step tasks.
install-openviking-memory
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…
proxy-config-skill
Configure residential proxy providers and make proxied HTTP requests with geo-targeting.
agentic-loop-skill
Autonomous decision loop with reflection and iteration.
progressive-discovery-skill
Discover and load tools progressively as needed (reduces token overhead).