From arcanon
This skill should be used when the user asks to "build the impact map", "scan my repos", "map service dependencies", "run /arcanon:map", or when an agent needs to build or query the service dependency graph. Provides cross-repo impact analysis using a local SQLite graph.
npx claudepluginhub arcanon-hub/arcanon --plugin arcanonThis skill uses the workspace's default tool permissions.
Build and query the Arcanon service dependency graph across one or more repositories.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Generates or updates index.md listing all files and subdirectories in a target folder with 3-10 word descriptions from file contents. Use for indexing documentation directories.
Build and query the Arcanon service dependency graph across one or more repositories.
This skill provides the same functionality as the /arcanon:map command. When invoked, it orchestrates the full scan lifecycle: repo discovery, user confirmation, agent-based scanning, finding persistence, and results display.
For full execution instructions, invoke the /arcanon:map command which contains the complete procedure for starting the worker, discovering repos, running agent scans, confirming findings, and persisting the map.
When this is the first successful map build (no prior map_versions, i.e., isFirstScan() returned true before this scan), output these recommendations to the user:
Map built successfully. To unlock the full Arcanon experience:
1. Enable semantic search (optional but recommended) Add to ~/.arcanon/settings.json:
{
"LIGAMEN_CHROMA_MODE": "local",
"LIGAMEN_CHROMA_HOST": "localhost",
"LIGAMEN_CHROMA_PORT": "8000"
}
Then start ChromaDB: docker run -p 8000:8000 chromadb/chroma
2. Add Arcanon impact checking to all your Claude agents
Create or update .mcp.json at your project root:
{
"mcpServers": {
"arcanon": {
"type": "stdio",
"command": "node",
"args": ["${CLAUDE_PLUGIN_ROOT}/worker/mcp/server.js"]
}
}
}
The /arcanon:map skill reads this section and outputs it verbatim after the first successful persist.
The check isFirstScan() from worker/db/database.js is called before writeScan() to determine whether to show this.