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.
/plugin marketplace add WinterDDo/claude-code-skill-autopilotnpx agentmods add plugins/winterddo/claude-code-skill-autopilot/skill-autopilotgit clone --depth 1 https://github.com/WinterDDo/claude-code-skill-autopilotGrade 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.
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"
}
}
}
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.
- 2d ago First seen · 33 lines scan A 506ef893b271
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.
Other plugins, from other repositories
tech-debt-mcp
Static technical-debt analysis across 14 languages, exposed as MCP tools and resources (SQALE ratings, debt summaries, custom rules, dependency vulnerabilities).
powerbi-report-builder
Build Power BI reports from natural language. Pages, visuals, themes, layouts, formatting — all PBIR-format.
code-quality
Code quality analysis, linting, and best practices enforcement.
commit-commands
Smart commit message generation and git workflow commands.
college-scorecard-mcp-server
Search, compare, and analyze U.S. college data — costs, earnings, programs, and outcomes — via MCP. STDIO or Streamable HTTP.
python-devtools marketplace
Plugin marketplace listing 1 plugin: python-devtools.