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 easyshell-ai/easyshell --skill easyshell-skillgit clone --depth 1 https://github.com/easyshell-ai/easyshellWrote 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/easyshell-ai/easyshell/easyshell-skill)<a href="https://agentmods.dev/skills/easyshell-ai/easyshell/easyshell-skill"><img src="https://agentmods.dev/badge/skills/easyshell-ai/easyshell/easyshell-skill/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.
<a href="https://agentmods.dev/skills/easyshell-ai/easyshell/easyshell-skill"><img src="https://agentmods.dev/badge/skills/easyshell-ai/easyshell/easyshell-skill.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.00940 |
| Opus 5.5 | $0.00021 | $0.00376 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo ago First seen · 120 lines · 52 tokens per session scan C d72130ce5ef9
easyshell is a skill published in the GitHub repository easyshell-ai/easyshell (79 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 940 once invoked, about $0.0002 per session on Opus 5.5. 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
perch
Server intelligence layer for RunCloud-managed Linux servers. Use when the user mentions Perch, /perch, RunCloud, nginx-rc, server intelligence, server diagnosis, WordPress site auditing, plugin vulnerability scanning, or any time they want to investigate, monitor, or heal a server they own.
lambda-gpu-cloud
Safely inspect and operate Lambda Cloud GPU instances through the documented Cloud API and SSH, with explicit approval before billable or destructive actions.
tensorpool-gpu-cloud
Safely inspect and operate TensorPool GPU clusters and jobs using the current tp CLI, with explicit approval before any billable or destructive action.
runpod-gpu-cloud
Safely inspect and operate RunPod resources with runpodctl, live product data, and explicit approval before paid or destructive actions.
vast-ai-gpu-cloud
Safely inspect and operate Vast.ai marketplace instances with the vastai CLI, live offer data, and explicit approval before paid or destructive actions.
dns-diagnose
A read-only tool for finding problems with domain-name resolution, the system that turns names such as example.com into server addresses. It checks local resolvers and DNS records for failures, wrong answers, or changes that are not visible yet.