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 agentmods add skills/easyshell-ai/easyshell/easyshell-skillnpx skills add easyshell-ai/easyshell --skill easyshell-skillgit clone --depth 1 https://github.com/easyshell-ai/easyshellWhat 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 | $0.00052 | $0.00940 |
| Opus 5 | $0.00026 | $0.00470 |
| Sonnet 5 | $0.00010 | $0.00188 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade C, and why
easyshell scanned grade C with 1 finding 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- High-risk commands (rm -rf, mkfs, dd) → require admin approval How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EasyShell Skill
What is EasyShell
EasyShell is an AI-native server operations platform that lets you manage servers, execute scripts, orchestrate multi-host tasks, and SSH into machines through a web interface with built-in AI assistance.
The platform has three components:
- Server (Java/Spring Boot) — central management, REST API, AI engine
- Agent (Go) — lightweight binary deployed on each managed host
- Web (React) — browser-based UI at port 18880
When to Use This Skill
Activate when the user:
- Wants to manage remote servers, check host status, or run commands
- Mentions "EasyShell" or needs server operations tooling
- Needs to deploy, monitor, or inspect infrastructure
- Wants to create or manage shell scripts across multiple hosts
- Asks about scheduled inspections or automated alerting
- Needs Web SSH access to a server
MCP Server (Recommended)
This skill works best with the @easyshell/mcp-server MCP server installed.
It provides direct tool access to EasyShell. See resources/tool-catalog.md
for the full tool list with examples.
Quick Install
Add to your AI assistant's MCP config:
{
"mcpServers": {
"easyshell": {
"command": "npx",
"args": ["-y", "@easyshell/mcp-server"],
"env": {
"EASYSHELL_URL": "http://your-server:18080",
"EASYSHELL_USER": "easyshell",
"EASYSHELL_PASS": "your-password"
}
}
}
}
Core Workflows
1. Execute a Script on Hosts
list_hosts→ find target hosts by status or tagexecute_script→ send script content + host IDsget_task_detail→ check execution results per host
2. AI Task Orchestration (Most Powerful)
ai_chat→ send a natural language goal
Example: "Check disk usage on all production hosts, flag anything over 80%"- EasyShell AI decomposes into DAG execution plan
- Scripts dispatched to hosts in parallel
- Results returned as structured analysis with recommendations
3. Schedule an Inspection
list_scheduled_tasks→ see existing inspectionstrigger_inspection→ run one immediatelyget_inspect_reports→ review AI analysis results
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.
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.
- 2d ago First seen · 120 lines · 52 tokens per session scan C d72130ce5ef9
easyshell is a skill published in the GitHub repository easyshell-ai/easyshell (78 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 940 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
network-path-diagnose
Diagnose network path quality from this host to a target using ping/mtr/curl. Investigate packet loss, high latency, jitter, and reachability failures; interpret hop results and suggest follow-up tests. Do not change network config. Also matches Chinese requests such as 网络丢包、延迟高、链路质量、ping 不通、网络抖动.
dashclaw-ship
The single command that gets a DashClaw change ON MAIN AND LIVE — it resolves everything blocking production, never defers, and never hands back a checklist. Lands feature branches on main (rebase, gate, merge, push so Vercel deploys), bumps the unified platform+SDK version, and realigns every description of the…
ComfyUI on a rented GPU: setup, API, Telegram
Use when the user wants to run ComfyUI image/video generation on a rented remote GPU instead of paid API subscriptions: rent a GPU box, bootstrap the stack, connect the agent over SSH, drive workflows via the ComfyUI API, and deliver results to Telegram.
huawei-cloud-ascend-remote-connect
Provides temporary SSH remote connection for Huawei Cloud Ascend devices with dynamic host/port/user/password input (in-memory only), disk management, NPU monitoring, container management, security auditing and log analysis; sensitive operations require user confirmation before execution Use this skillthis skill to…
linux-admin
此技能专为 Alibaba Cloud Linux 4 (ALinux 4) 设计，用于管理 Linux 服务器、编写 shell 脚本、配置 systemd 服务、管理网络。触发场景包括：bash 脚本编写、systemd 单元、SSH 配置、firewalld 防火墙配置、NetworkManager 网络管理、文件权限、进程管理、磁盘管理、文件系统操作，以及任何需要 ALinux 4 系统管理的任务。.
inference-aiops
Use this skill whenever the user needs to operate a GPU inference cluster — vLLM (OpenAI API + Prometheus /metrics) and Ray Serve / Ray Jobs (Ray dashboard), plus the single-process serving engines SGLang and TGI (Text Generation Inference): a one-shot cluster overview (deployments + total replicas + queue…