Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

system-info — Claude Code skill: what it does, how to install

A skill with two scripts that tell the agent which host it runs on and what sits in a folder. Useful before you trust any path it prints.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add agno-agi/agno --skill system-info -a claude-code
Open on GitHub

What system-info does

The skill ships two scripts. get_system_info.py reports hostname, operating system, architecture, Python version and its executable path, processor and the current UTC time. list_directory.py lists the direct children of a folder; the path argument is optional and falls back to the skill directory.

The agent runs them through the get_skill_script tool, passing the skill name, the script path and execute=True, then reads the structured result rather than raw terminal output.

One rule carries the rest: parse stdout only when returncode is 0. On a nonzero code, report stderr or the JSON error instead of guessing. Worth checking how your agent handles that failure path, because a confident wrong line about the host costs more than an empty answer.

Scope is the host running the AgentOS process, not a remote machine.

What it helps with

  • Read OS, architecture and Python version on the agent host
  • List a directory's direct children without recursion
  • Tell a successful script run from a failed one via returncode
  • Capture hostname, processor and UTC time in one report
  • Find where the Python interpreter lives

Example prompts for the agent

  • Which OS and Python version is this host running?
  • List the contents of `.` using `list_directory.py`
  • Give me a system report: hostname, architecture, processor, UTC time

How to install system-info

1Skills CLI (Vercel)

npx skills add agno-agi/agno --skill system-info -a claude-code

2Manually: put the files in place

~/.claude/skills/system-info/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/system-info/

From the same set3

The whole set →
git-workflow agno-team A skill that enforces best practices for commits, branch names, and pull requests. Includes commit message validation, branch naming templates, and PR checklist structure — useful if your team has git standards. Claude Code CX Codex Cursor +1 665installs code-review agno-team Automated code inspection for style violations, bugs, and best-practice gaps. The skill runs linting, identifies issues, and delivers structured feedback with severity levels. Claude Code CX Codex Cursor +1 472installs

Similar

handoff thedotmack Generates a structured HANDOFF.md with goals, failed attempts, and next steps. Use it when context degrades or when starting a fresh session. Claude Code CX Codex Cursor +1 344installs obsidian-canvas-creator axtonliu Turns text into a JSON Canvas file that Obsidian opens as an interactive board. Choose a radial mind map or a freeform layout with grouped zones. Claude Code CX Codex Cursor +1 2,000installs firecrawl-build-search firecrawl A skill that shows an agent how to wire Firecrawl search into a product, so a query finds candidate pages before anything gets read. Claude Code CX Codex Cursor +1 61,500installs skill-creator tldraw A guide the agent follows while building a skill: what belongs in SKILL.md, what goes into scripts/, references/ and assets/, and how to keep the whole thing short. Claude Code CX Codex Cursor +1 431installs firecrawl-build-interact firecrawl A coding-agent skill that gets Firecrawl /interact into product code when a page has to be clicked, filled in or paged through before you can read it. Claude Code CX Codex Cursor +1 61,200installs firecrawl-build-onboarding firecrawl Skill fetches Firecrawl credentials and sets up the SDK in your project via built-in browser authentication. Use when your app needs FIRECRAWL_API_KEY or you're adding Firecrawl to .env. Claude Code CX Codex Cursor +1 61,200installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs

Questions about system-info

How do I install system-info in Claude Code?

Run npx skills add agno-agi/agno --skill system-info -a claude-code. The skill file lands at ~/.claude/skills/system-info/SKILL.md.

What does system-info do?

It returns host details: hostname, OS, architecture, Python version and executable path, processor and UTC time. The second script lists one directory level.

How should the agent handle a script error?

Use stdout only when returncode is 0. On a nonzero code it should report stderr or the JSON error rather than infer a result.

Source text

SKILL.md · MIT 
---
name: system-info
description: Inspect the host operating system, Python runtime, and local files
license: MIT
metadata:
  version: "1.0.0"
  author: agno
---
# System Info Skill

Use this skill when the user asks about the host running the AgentOS process or
needs a directory inventory from that host.

## Available scripts

- `get_system_info.py` returns the hostname, operating system, architecture,
  Python version and executable, processor, and current UTC time.
- `list_directory.py` lists the direct children of a directory. It accepts one
  optional path argument and defaults to the skill directory.

## Execution

Load these instructions before choosing a script. Execute a script through the
skill tool and inspect its structured result:

```python
get_skill_script(
    skill_name="system-info",
    script_path="get_system_info.py",
    execute=True,
)
```

To list a directory:

```python
get_skill_script(
    skill_name="system-info",
    script_path="list_directory.py",
    execute=True,
    args=["."],
)
```

Only use data parsed from `stdout` when `returncode` is `0`. If execution
returns a nonzero code, report `stderr` or the JSON error instead of inferring
the result.

© agno · MIT · agno-agi/agno

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor