roach

Plugin roach from marketplace roach-marketplace in stefanfaur/roach-marketplace. Commands read from the repo's manifest — 1 month ago.

Skills (18)

• brainstorming

  Use before any creative work — creating features, building components, adding functionality, or modifying behavior — before writing code or invoking an implementation skill.

• committing

  Use when creating git commits with user approval, whether committing explicit file paths or auto-discovering all changes

• create-handoff

  Use when context is getting long, before pausing or ending a work session, or when transferring ongoing work to a new session — prefer this over auto-compacting, and write it before context fills up.

• dispatching-parallel-agents

  Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

• executing-plans

  Use when implementing a written plan task by task, in this session or a new one

• grill-me

  Use when the user wants their plan or design stress-tested — poke holes, challenge assumptions, devil's-advocate pushback — mentions "grill me", or arrives at brainstorming with a design already in their head.

• receiving-code-review

  Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

• requesting-code-review

  Use when completing tasks, implementing major features, or before merging to verify work meets requirements. Invoke with arguments: BASE_SHA HEAD_SHA 'what was implemented' 'plan path or requirements' — without the two SHAs it reviews the wrong diff.

• researching-codebase

  Use when documenting codebase as-is through parallel agent research, producing a research document in thoughts/ to answer a specific question about how existing code works

• resuming-handoff

  Use when resuming work from a handoff document, given its path or a domain name

• systematic-debugging

  Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

• test-driven-development

  Use when implementing any feature or bugfix, before writing implementation code

• using-roach

  Use when starting any conversation — explains how to find and invoke roach skills before responding or acting, including before clarifying questions

• verification-before-completion

  Use when about to claim work is complete, fixed, or passing — before committing, opening a PR, marking a task done, or reporting success to the user or a controller

• writing-natural

  Use when writing any natural language — documentation, READMEs, changelogs, summaries, skill content, command content, or any prose that will be read by humans.

• writing-plans

  Use when you have a spec or requirements for a multi-step task, before touching code

• writing-simply

  Use when writing any natural language that will be read by humans: documentation, READMEs, changelogs, summaries, PR descriptions, release notes, error messages, or skill content. Applies when plain controlled prose is wanted over prose with a voice. Also use when asked to remove AI slop, stop text

• writing-skills

  Use when creating new skills, editing existing skills, or verifying skills work before deployment

Subagents (7)

• code-reviewer

  Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: <example>Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing

• codebase-analyzer

  Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :)

• codebase-locator

  Locates files, directories, and components relevant to a feature or task. Call `codebase-locator` with human language prompt describing what you're looking for. Basically a "Super ripgrep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.

• codebase-pattern-finder

  codebase-pattern-finder is a useful subagent_type for finding similar implementations, usage examples, or existing patterns that can be modeled after. It will give you concrete code examples based on what you're looking for! It's sorta like codebase-locator, but it will not only tell you the locatio

• thoughts-analyzer

  The research equivalent of codebase-analyzer. Use this subagent_type when wanting to deep dive on a research topic. Not commonly needed otherwise.

• thoughts-locator

  Discovers relevant documents in thoughts/ directory (We use this for all sorts of metadata storage!). This is really only relevant/needed when you're in a reseaching mood and need to figure out if we have random thoughts written down that are relevant to your current research task. Based on the name

• web-search-researcher

  Do you find yourself desiring information that you don't quite feel well-trained (confident) on? Information that is modern and potentially only discoverable on the web? Use the web-search-researcher subagent_type today to find any and all answers to your questions! It will research deeply to figure

Hooks (1)

• SessionStart

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh

Similar plugins