skill-autopilot

A local Claude Code plugin that recommends which installed skills fit the current task and can suggest useful commands.

In plain words
What is it for?
Use it to route each prompt to relevant installed skills, with settings for guidance style, language, and automatic planning.
Why use it?
It reduces the chance of forgetting a relevant skill or missing a helpful command during a session.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add WinterDDo/claude-code-skill-autopilot
agentmods
npx agentmods add plugins/winterddo/claude-code-skill-autopilot/skill-autopilot
Clone the repo
git clone --depth 1 https://github.com/WinterDDo/claude-code-skill-autopilot

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

skill-autopilot 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 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.

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.

plugins/skill-autopilot/.claude-plugin/plugin.json · 33 lines

What it actually says

{
  "name": "skill-autopilot",
  "version": "1.0.0",
  "description": "Use all the skills you've installed — not just the ones you remember. Each turn it surfaces the installed skills most relevant to your task, so a fitting one is in front of you instead of forgotten. Also offers high-leverage commands when they fit; handles the basics silently. Open source, zero telemetry, local-first.",
  "author": {
    "name": "Win"
  },
  "license": "MIT",
  "homepage": "https://github.com/WinterDDo/claude-code-skill-autopilot",
  "repository": "https://github.com/WinterDDo/claude-code-skill-autopilot",
  "hooks": "./hooks/hooks.json",
  "userConfig": {
    "aggressiveness": {
      "type": "string",
      "title": "Aggressiveness",
      "default": "teaching",
      "description": "teaching | normal | quiet. teaching = silent help + command tips; normal = silent help, tips only at costly misses; quiet = silent help only"
    },
    "language": {
      "type": "string",
      "title": "Guidance language",
      "default": "en",
      "description": "en or zh — language of injected guidance"
    },
    "enable_plan_gate": {
      "type": "boolean",
      "title": "Auto plan mode",
      "default": true,
      "description": "Automatically enter plan mode before substantial design/build/refactor work"
    }
  }
}
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 · 33 lines scan A 506ef893b271

Subscribe to this mod's changes

skill-autopilot is a plugin published in the GitHub repository WinterDDo/claude-code-skill-autopilot (6 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.