Agent skill · AI & Agents

openloomi-hooks

OpenLoomi × Claude Code hooks installer. Use when the user wants Claude Code's lifecycle (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop, Notification) to mirror onto the Loomi Pet, or wants to auto-archive every Stop into OpenLoomi memory. Triggers: install hooks, /openloomi:hooks, hooks install, hooks uninstall, hooks status, mirror claude on pet, auto-archive stop.

melandlabsgithub.com/melandlabsGitHub ↗
claude-coderead-onlyApache-2.0
Install
npx skills add melandlabs/openloomi --skill openloomi-hooks --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 2 KB
Bundled scripts: none
Allowed tools: Bash(node${CLAUDE_PLUGIN_ROOT}/scripts/loomi-bridge.mjs*)
Path: plugins/claude/skills/openloomi-hooks/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 764
Language: TypeScript

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# OpenLoomi Hooks Sub-skill The plugin ships a hook bundle in `hooks/hooks.json` but **never installs it automatically**. Users must explicitly run one of: - `/openloomi:hooks install` — merge the bundle into `~/.claude/settings.json` - `/openloomi:hooks uninstall` — strip only the plugin's block (other plugins' hooks are preserved) - `/openloomi:hooks status` — report whether the bundle is currently active Under the hood this calls: ```bash node ${CLAUDE_PLUGIN_ROOT}/scripts/loomi-bridge.mjs install-hooks node ${CLAUDE_PLUGIN_ROOT}/scripts/loomi-bridge.mjs uninstall-hooks node ${CLAUDE_PLUGIN_ROOT}/scripts/loomi-bridge.mjs hooks-status ``` ## Safety guarantees - `install-hooks` is **merge-no-overwrite**: only adds the plugin's block under `hooks.__openloomi_claude_plugin_hooks__`. Existing hooks for other plugins are not touched. - `uninstall-hooks` removes only the plugin-marked block; rerunning it after the first time reports `removed: false`, never deletes anything else's hooks. - The merge is atomic (`writeFile` to a temp file, then `rename`). - The Stop hook **always exits 0** — archive failures are reported as JSON `{continue: true, _openloomi: {archive: "skipped", reason: .

What's inside
Steps it walks through
  1. Safety guarantees
  2. Suggested user prompt
Commands it runs
node ${CLAUDE_PLUGIN_ROOT}/scripts/loomi-bridge.mjs install-hooks
node ${CLAUDE_PLUGIN_ROOT}/scripts/loomi-bridge.mjs uninstall-hooks
node ${CLAUDE_PLUGIN_ROOT}/scripts/loomi-bridge.mjs hooks-status
More from openloomi
All skills →
About this skill
What does the openloomi-hooks skill do?

OpenLoomi × Claude Code hooks installer. Use when the user wants Claude Code's lifecycle (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop, Notification) to mirror onto the Loomi Pet, or wants to auto-archive every Stop into OpenLoomi memory. Triggers: install hooks, /openloomi:hooks, hooks install, hooks uninstall, hooks status, mirror claude on pet, auto-archive stop.

How do I install it?

Run `npx skills add melandlabs/openloomi --skill openloomi-hooks --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From melandlabs/openloomi, a repository with 764 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going