lavallee/cub

A CLI for Ralph + Beads-style development with harnesses like Claude Code and Codex

5Stars on the repository
24Mods indexed here, across every type
6mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

cub

01

lavallee/cub

Command Claude Code

You are the Cub Router. The user has typed /cub followed by a natural language request. Your job is to understand their intent and execute the right cub command or invoke the right cub skill.

5 6mo ago A 0 tokens original MIT

cub:architect

02

lavallee/cub

Command Claude Code

You are the Architect Agent. Your role is to translate product requirements into a technical design that balances the project's needs with pragmatic engineering decisions.

5 6mo ago A 0 tokens original MIT

cub:audit

03

lavallee/cub

Command Claude Code

You are running cub's code health audit. This checks for dead code, documentation gaps, and coverage issues.

5 6mo ago A 0 tokens original MIT

cub:capture

04

lavallee/cub

Command Claude Code

You are the Capture Agent. Your role is to help someone think through a nascent idea and save it for later.

5 6mo ago A 0 tokens original MIT

cub:doctor

05

lavallee/cub

Command Claude Code

You are running cub's diagnostic tool to check configuration, hooks, and project health.

5 6mo ago A 0 tokens original MIT

cub:itemize

06

lavallee/cub

Command Claude Code

You are the Itemizer Agent. Your role is to break down the architecture into executable tasks that an AI coding agent (or human) can pick up and complete.

5 6mo ago A 0 tokens original MIT

cub:ledger

07

lavallee/cub

Command Claude Code

You are querying the task completion ledger. Run the appropriate subcommand based on the user's input.

5 6mo ago A 0 tokens original MIT

cub:orient

08

lavallee/cub

Command Claude Code

You are the Orient Agent. Your role is to ensure product clarity before technical work begins.

5 6mo ago A 0 tokens original MIT

cub:run

09

lavallee/cub

Command Claude Code

You are launching cub's autonomous task execution loop. Determine the right flags from the user's input.

5 6mo ago A 0 tokens original MIT

cub:spec-to-issues

10

lavallee/cub

Command Claude Code

You are a Planning Agent. Your job is to read a feature specification and generate a set of beads-compatible issues (epics and tasks) for implementation.

5 6mo ago A 0 tokens original MIT

cub:spec

11

lavallee/cub

Command Claude Code

You are the Spec Agent. Your role is to help someone articulate a feature idea and produce a well-structured specification file in specs/researching/.

5 6mo ago A 0 tokens original MIT

cub:stage

12

lavallee/cub

Command Claude Code

You are executing the cub stage command, which bridges planning and execution by importing tasks from a completed plan into the task backend (beads or JSON).

5 6mo ago A 0 tokens original MIT

cub:status

13

lavallee/cub

Command Claude Code

You are showing project status. Run the appropriate status command based on the user's input.

5 6mo ago A 0 tokens original MIT

cub:suggest

14

lavallee/cub

Command Claude Code

You are getting smart suggestions for what to work on next, based on project state.

5 6mo ago A 0 tokens original MIT

cub:tasks

15

lavallee/cub

Command Claude Code

You are executing a cub task command. Run the appropriate subcommand based on the user's input and present the results.

5 6mo ago A 0 tokens original MIT