A guide and toolset for keeping an SSH connection open while sending and receiving commands over time. SSH is a way to open a command shell on another computer securely.

Use it to start, reuse, inspect, and stop named remote SSH sessions, including sessions that continue running while you do other work.

It avoids reconnecting for every command and helps handle prompts, streamed output, and long-running remote work in one session.

ssh-async — Skill for Claude Code and Codex by 02loveslollipop: A guide and toolset for keeping an SSH connection…

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/02loveslollipop/opencrow/ssh-async

Any agent

npx skills add 02loveslollipop/OpenCROW --skill ssh-async

Clone the repo

git clone --depth 1 https://github.com/02loveslollipop/OpenCROW

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/02loveslollipop/opencrow/ssh-async.svg)](https://agentmods.dev/skills/02loveslollipop/opencrow/ssh-async)

Your own site

<a href="https://agentmods.dev/skills/02loveslollipop/opencrow/ssh-async"><img src="https://agentmods.dev/badge/skills/02loveslollipop/opencrow/ssh-async.svg" alt="Measured on agentmods" height="20"></a>

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 867 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5	$0.00077	$0.00867
Opus 5	$0.00039	$0.00434
Sonnet 5	$0.00015	$0.00173
Haiku 4.5	$0.00008	$0.00087

Measured 4d ago against content hash 8db8c2572490, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ssh-async 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/ssh_async_session.py), 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/ssh-async/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenCROW I/O - SSH Async

Runtime preflight

Probe required commands with command -v and Python modules with importlib.util.find_spec before use. Prefer a PATH-resolved OpenCROW MCP helper or the ctf/sage environment when available, then the managed helper or system Python. If a capability is missing, stop that path safely and report the exact missing command or module.

Prefer the opencrow-ssh-mcp server for session lifecycle, reads, and writes. Fall back to scripts/sshx only when you need to inspect or debug the backend directly.

MCP First

Use toolbox_info, toolbox_verify, and toolbox_capabilities first.
Use the generic session tools:
- session_start
- session_send
- session_read
- session_status
- session_stop
Keep one named session per host/task flow so the MCP server can return stable artifacts under /tmp/opencrow-ssh-async/<name>/.

Use scripts/sshx to manage long-lived SSH sessions instead of one-shot ssh invocations when you are operating outside MCP.

Workflow

Start a named session to a remote host.
Send shell input while the daemon keeps receiving remote output asynchronously.
Read logs with --tail for recent context or --follow for streaming output.
Stop the session explicitly when done.

Commands

# Start an interactive login shell
scripts/sshx start --name demo --host 10.0.0.5 --user ubuntu

# Start with a specific identity file and port
scripts/sshx start --name prod --host prod.example.com --user deploy --port 2222 \
  --identity ~/.ssh/deploy_ed25519

# Send a command to the open shell
scripts/sshx send --name prod --data 'uname -a' --newline

# Read recent output
scripts/sshx read --name prod --tail 60

# Follow output live
scripts/sshx read --name prod --follow

# Inspect metadata and process state
scripts/sshx status --name prod

# Stop the session
scripts/sshx stop --name prod

Operational Rules

Use one session per host/task flow so prompts, working directory, and shell state stay coherent.
Prefer key-based authentication. The helper runs ssh in batch mode and will fail fast instead of hanging on password prompts.
Append --newline for normal shell commands.
Read with --tail before --follow so prompt/output context is visible first.
Stop sessions explicitly to avoid leaving remote shells running.
If status reports running: false, inspect daemon.log and io.log before restarting.

Read the full file on GitHub · 88 lines

Files

What ships with it

3 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.

4d ago First seen · 88 lines · 77 tokens per session scan A 8db8c2572490

Subscribe to this mod's changes

ssh-async is a skill published in the GitHub repository 02loveslollipop/OpenCROW (8 stars, last pushed today), licensed Apache-2.0. It adds 77 tokens to every session and 867 once invoked, about $0.0004 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 2026-08-31.

Planning agent-orchestration agent-runtime agentic-ai ai-agents ctf cybersecurity

ctf-web

CTF Web攻击知识库 — PHP弱比较绕过、命令注入空格绕过、eval回显技巧、SSTI注入链、反序列化利用链、PHP代码审计checklist、常见flag位置.

Netw0rkNoob/VulnClaw · 56 tokens

osint-recon

OSINT 开源情报收集知识库 — 四维信息收集模型（服务器→网站→域名→人员），维度四（人员信息）条件触发.

Netw0rkNoob/VulnClaw · 42 tokens

crypto-toolkit

编码解码与加解密工具 — base64/URL/Hex/HTML实体编码解码，MD5/SHA哈希，AES/DES/RSA加解密，JWT解析，Caesar/ROT13密码，栅栏/Vigenere密码，Unicode转义，Morse电码等.

Netw0rkNoob/VulnClaw · 69 tokens

hackerone

HackerOne 赏金项目 scope-guard 流程 — 读取 program scope，强制 scope 与 program rules，再逐个把 in-scope asset 交给 pentest-flow.

Netw0rkNoob/VulnClaw · 43 tokens

redteam-cve-lookup

CVE lookup and applicability assessment domain card. Use after reconnaissance has identified products, versions, services, or fingerprints and red-team mode needs evidence-based CVE matching before deeper testing.