plugins/learning-output-style/.claude-plugin/plugin.json

{
  "name": "learning-output-style",
  "version": "1.0.0",
  "description": "Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)",
  "author": {
    "name": "Anthropic",
    "email": "support@anthropic.com"
  }
}
creating intital scaffolding for claude code plugins 2025-11-20 11:47:24 -08:00			`{`
			`"name": "learning-output-style",`
fix: invoke .sh hooks via bash prefix; add version for cache invalidation Fixes #993 (Permission denied on hook scripts) without relying on client-side +x preservation. The hook executor spawns commands via /bin/sh -c, which requires +x to execute a script directly. Prefixing with bash reads the script as data — mode bits are irrelevant. This works on all Claude Code versions, whereas the client-side chmod fix (claude-cli #24666) only shipped in v2.1.86. All 3 scripts declare #!/bin/bash and use bashisms ([[ ]], =~), so bash (not sh) is the correct interpreter. The version field forces a fresh cache path (1.0.0/ instead of unknown/), ensuring the new hooks.json reaches users with stale caches. 2026-03-28 08:40:34 -07:00			`"version": "1.0.0",`
creating intital scaffolding for claude code plugins 2025-11-20 11:47:24 -08:00			`"description": "Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)",`
			`"author": {`
Update plugins library to include authors (#6) * added Anthropic as author * update figma 2025-12-12 16:52:17 -08:00			`"name": "Anthropic",`
			`"email": "support@anthropic.com"`
creating intital scaffolding for claude code plugins 2025-11-20 11:47:24 -08:00			`}`
			`}`