jumpserver-agent-skill

An operating guide for using jumpserver-ssh-mcp to reach remote machines through a JumpServer gateway. A gateway is an intermediate access point used to connect to a target host.

In plain words
What is it for?
Use it to install or update the access tools, configure a gateway and target, validate the connection, transfer files, run remote jobs, and repair matchers when login prompts are not recognized.
Why use it?
It organizes setup, login testing, file transfer, long-running commands, and repair of failed connection matching without requiring the user to write internal configuration.

Skill for Claude CodeCodex

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/shadow-linux/jumpserver_ssh_mcp/jumpserver-agent-skill
Any agent
npx skills add Shadow-linux/jumpserver_ssh_mcp --skill jumpserver-agent-skill
Clone the repo
git clone --depth 1 https://github.com/Shadow-linux/jumpserver_ssh_mcp

Made for: Claude Code, Codex.

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,442 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00056 $0.01442
Opus 5 $0.00028 $0.00721
Sonnet 5 $0.00011 $0.00288
Haiku 4.5 $0.00006 $0.00144

Measured 2d ago against content hash e64756f0fa2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jumpserver-agent-skill scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Keep Base64/direct portable `ssh.file_push` / `ssh.file_pull` to files up to 50MB. When Koko SFTP is unavailable, use remote `curl` / `wget`, object storage, or direct SSH rsync for larger artifacts.
skills/jumpserver-agent-skill/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JumpServer Agent Skill

Overview

Use jumpserver-ssh-mcp as the capability layer and this skill as the operating playbook. The human should only need to provide a gateway name, a JumpServer SSH login command, and a target host; the Agent owns configuration, probe, smoke test, and matcher repair.

Agent Responsibility

The Agent must perform the operational setup work itself. Do not ask the human to hand-write profile internals or matcher JSON unless they explicitly want to.

Human-provided inputs should stay small:

  • gateway name
  • JumpServer SSH login command
  • target host/IP or asset identifier for validation
  • optional preferred asset account

Agent-owned outputs:

  • MCP source installation or upgrade when requested
  • Agent Skill installation when supported by the client
  • MCP client configuration
  • SSH_ASSIST_PROFILE profile file
  • gateway entry
  • matcher selection
  • custom matcher JSON when built-in matchers fail
  • probe and smoke-test evidence

Built-in matchers are packaged inside jumpserver-ssh-mcp and are available after installation. Agent-authored matchers should be written only to configured custom matcher directories, usually ~/jumpserver-ssh-mcp/matchers/.

Required Inputs

Ask for only missing essentials:

  • gateway_name, such as pro-jumpserver or test-jumpserver
  • JumpServer SSH login command, such as ssh -i ~/.ssh/pro.pem [email protected] -p2222
  • one target host or asset identifier for validation

Optional:

  • preferred asset account, such as root, __su, or deploy
  • environment label, such as prod or test

Workflow

  1. If the MCP or this Skill is missing, outdated, or exposes only part of the native Job tools, read references/install-and-upgrade.md and complete installation or upgrade first.
  2. Read references/mcp-client-config.md and configure the Agent client when the MCP entry is missing or stale.
  3. Read references/profile-authoring.md before creating or changing a profile file.
  4. Read references/onboard-gateway.md before probing a gateway.
  5. Create or update the profile using the simple gateway shape; do not expose internal fields like type: interactive_expect unless maintaining legacy config.
  6. Start with matcher: builtin-generic unless a known reference matcher fits better.
  7. Call ssh.matcher_list to verify available matchers and configured gateways.
  8. Call ssh.matcher_probe with the target host and gateway. This must not execute a remote command.
  9. If probe succeeds, run one non-destructive smoke command with ssh.run_command, such as hostname; whoami; id. Pass a stable owner_id for the current Agent/thread when the MCP tool supports it.
  10. If probe fails because the JumpServer screen is not matched, read the MCP matcher docs and write a custom declarative matcher.
  11. Validate custom matcher with ssh.matcher_validate, replay transcript snippets with ssh.matcher_test_transcript, then rerun ssh.matcher_probe.
  12. Record the final gateway name, profile path, matcher name, target used for validation, and smoke evidence.
  13. Before starting a download, build, install, or other long-running command, read references/background-jobs.md and select the native or compatibility route by MCP tool capability.

Read the full file on GitHub · 96 lines

Files

What ships with it

6 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.

  1. 2d ago First seen · 96 lines · 56 tokens per session scan A e64756f0fa2d

Subscribe to this mod's changes

jumpserver-agent-skill is a skill published in the GitHub repository Shadow-linux/jumpserver_ssh_mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,442 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens