claudemods

All Claude Code mods4DvAnCeBoY/rook-claude-plugin

rook

A Claude Code mod in 4DvAnCeBoY/rook-claude-plugin

rook by TestMu AI inside Claude Code: Claude runs rook against the agent it is building and gets failures back grouped into root-cause clusters with rook's remedies, writes scenarios, a live pane with per-scenario lanes and openable failures, re-test prompts after agent edits, a status line score, /rook commands and a production-target guard.

rook reaches L2 (writes or runs) by its classified calls and passed claude plugin validate on Claude Code 2.1.302.

Install hint

/plugin install rook --marketplace 4DvAnCeBoY/rook-claude-plugin

From the repository's own marketplace. Confirm the plugin name in the repository's README before installing. Mods need Claude Code 2.1.287 or later.

Access

L2 Writes or runsother: $.process.spawn, other: $.state.get, other: $.state.set, runs processes, writes files, changes config, drives Claude, writes the prompt box, reads files, reads env vars, persists state, draws

Validation

Passed on Claude Code 2.1.302

View the source on GitHub Back to the list

What the scan recorded

Observed events
/"^mcp__rook__run$"/ calls, /"^mcp__rook__report$"/ calls, /"^mcp__rook__status$"/ calls, /"^mcp__rook__scenarios$"/ calls, /"^mcp__rook__runs$"/ calls, /"^mcp__rook__agent$"/ calls, /"^mcp__rook__curate$"/ calls, /"^mcp__rook__generate$"/ calls, /"^mcp__rook__project$"/ calls, /"^mcp__rook__explore$"/ calls, /"^mcp__rook__profile_test$"/ calls, /"^mcp__rook__compare$"/ calls, /"^mcp__rook__sync$"/ calls, /"^mcp__rook__ci$"/ calls, Bash calls, /"^(Edit|Write|MultiEdit|NotebookEdit)$"/ calls
Hooks
session.start, tool.call {tool=/"^mcp__rook__run$"/}, tool.call {tool=/"^mcp__rook__report$"/}, tool.call {tool=/"^mcp__rook__status$"/}, tool.call {tool=/"^mcp__rook__scenarios$"/}, tool.call {tool=/"^mcp__rook__runs$"/}, tool.call {tool=/"^mcp__rook__agent$"/}, tool.call {tool=/"^mcp__rook__curate$"/}, tool.call {tool=/"^mcp__rook__generate$"/}, tool.call {tool=/"^mcp__rook__project$"/}, tool.call {tool=/"^mcp__rook__explore$"/}, tool.call {tool=/"^mcp__rook__profile_test$"/}, tool.call {tool=/"^mcp__rook__compare$"/}, tool.call {tool=/"^mcp__rook__sync$"/}, tool.call {tool=/"^mcp__rook__ci$"/}, tool.call {tool=Bash}, tool.call {tool=/"^(Edit|Write|MultiEdit|NotebookEdit)$"/}, command.run {command=rook}, ui.message, ui.render {component=ToolResult, props has {tool=?}, ui.render {component=ToolUse, props has {tool=?}, ui.render {component=Spinner}, ui.render {component=Pane, requestId=rook}, ui.render {component=AbovePrompt}
API calls
$.clock.after, $.clock.every, $.clock.now, $.command.register, $.config.set, $.env.get, $.fs.exists, $.fs.list, $.fs.read, $.fs.write, $.process.run, $.process.spawn, $.prompt.fill, $.prompt.submit, $.session.append, $.state.get, $.state.set, $.store.get, $.store.set, $.tool.register, $.ui.focus, $.ui.invalidate, $.ui.open, $.ui.resolve, $.ui.status, $.ui.toast
Surface modules
hooks/heat.client.tsx
Validation on 2.1.302
Passed
Scanned revision
dfa2b8c17961
Marketplace passed
rook-claude-plugin

These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. How the scan works.

Badge for your README

Reach badge for rook Validation badge for rook

Authors can show the latest scan result in their README. Each badge links to this page.

[![reach](https://raw.githubusercontent.com/karanb192/awesome-claude-code-mods/main/badges/4DvAnCeBoY--rook-claude-plugin--rook-reach.svg)](https://mods.aidojo.si/mods/4DvAnCeBoY--rook-claude-plugin--rook/)
[![validates](https://raw.githubusercontent.com/karanb192/awesome-claude-code-mods/main/badges/4DvAnCeBoY--rook-claude-plugin--rook-validates.svg)](https://mods.aidojo.si/mods/4DvAnCeBoY--rook-claude-plugin--rook/)