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/hkuds/cli-anything/cli-anything-jumpservernpx skills add HKUDS/CLI-Anything --skill cli-anything-jumpservergit clone --depth 1 https://github.com/HKUDS/CLI-AnythingWrote 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/hkuds/cli-anything/cli-anything-jumpserver)<a href="https://agentmods.dev/skills/hkuds/cli-anything/cli-anything-jumpserver"><img src="https://agentmods.dev/badge/skills/hkuds/cli-anything/cli-anything-jumpserver.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 | $0.00049 | $0.02480 |
| Opus 5 | $0.00024 | $0.01240 |
| Sonnet 5 | $0.00010 | $0.00496 |
| Haiku 4.5 | $0.00005 | $0.00248 |
Grade A, and why
cli-anything-jumpserver 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.
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.
How it starts
The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cli-anything-jumpserver
Stateful CLI harness for JumpServer bastion host. Manage assets, users, permissions, accounts, sessions, audits, and more via the JumpServer REST API.
Quick Start
# Install
cd agent-harness && pip install -e .
# Authenticate
cli-anything-jumpserver auth login --url https://jumpserver.example.com --username admin
# List hosts
cli-anything-jumpserver asset list --type host
# Interactive REPL mode
cli-anything-jumpserver --interactive
Agent Usage Guidance
This CLI is designed for AI agent consumption. Key features for agents:
JSON Output Mode
All commands support --output json for machine-parseable output:
cli-anything-jumpserver asset list --type host --output json
Dry Run Mode
All mutation commands support --dry-run to preview without execution:
cli-anything-jumpserver asset create --name test --address 10.0.0.1 --platform 1 --dry-run --output json
Environment Variables
JUMPSERVER_URL- Default JumpServer URLJUMPSERVER_USERNAME- Default usernameJUMPSERVER_PASSWORD- Default password
Typical Agent Workflows
1. Discovery and Inventory
# Check connection
cli-anything-jumpserver auth status --output json
# List all hosts
cli-anything-jumpserver asset list --type host --output json
# Get asset details
cli-anything-jumpserver asset get <ID> --type host --output json
# List all users
cli-anything-jumpserver user list --output json
2. User and Permission Management
# Create user
cli-anything-jumpserver user create --name "New User" --username newuser --email [email protected] --output json --dry-run
# Grant asset access
cli-anything-jumpserver perm create --name "App Access" --users "user1,user2" --assets "asset1,asset2" --output json --dry-run
# Verify permissions
cli-anything-jumpserver perm users <PERM_ID> --output json
3. Security Audit
# Check failed logins
cli-anything-jumpserver audit login --status failed --output json
# Review operations
cli-anything-jumpserver audit operate --action delete --output json
# Check active sessions
cli-anything-jumpserver session list --active --output json
# View command history
cli-anything-jumpserver session command list --risk 5 --output json
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 · 351 lines · 49 tokens per session scan A 142a1cae2d99
cli-anything-jumpserver is a skill published in the GitHub repository HKUDS/CLI-Anything (48,809 stars, last pushed 13d ago), licensed Apache-2.0. It adds 49 tokens to every session and 2,480 once invoked, about $0.0002 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
omniwire
Infrastructure layer for AI agent swarms — 88 MCP tools for mesh control, A2A protocol, OmniMesh VPN, CyberSync, web scraping, firewall management, browser automation, and more. 80ms execution.
ansible
Ansible IT automation reference. Agentless SSH-based architecture, static/dynamic inventory with groups, YAML playbooks with tasks/handlers/tags, 3000+ built-in modules, role directory structure, Ansible Vault secrets encryption, Galaxy collections, and production best practices.
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.
runpod-gpu-cloud
Safely inspect and operate RunPod resources with runpodctl, live product data, and explicit approval before paid 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.
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.