Drive a refined Linear issue end-to-end — loop its child sub-issues through plan → execute → review → Linear update + state move.
Gera uma mensagem de commit convencional a partir do diff staged (não faz commit).
Generate or refresh RC project documentation — README, Postman collection, and OpenAPI spec.
Execute the implemented RC tasks for a feature using the rc-execute-task skill.
Adversarial generator↔evaluator loop to drive subjective quality (UI/UX, CLI ergonomics, copy) up to a target score by exercising the running artifact.
Council archetype — the systems and long-horizon advisor. Dispatched by the council skill when service boundaries, data ownership, long-term coupling, or scaling are at stake. Argues for system boundaries, coupling and cohesion, consistency, technical-debt control, and 10x/100x scalability. Not for standalone use outside a council session.
Council archetype — the informed skeptic. Dispatched by the council skill when consensus forms too quickly, a plan looks solid, or the group is over-aligned. Surfaces hidden assumptions, edge cases, and failure modes; stress-tests the strongest form of every argument. Not for standalone use outside a council session.
Council archetype — the execution-reality advisor. Dispatched by the council skill for debates involving new frameworks, rewrites, migration cost, or team ramp-up. Argues for what works today, maintenance burden, team velocity, incremental delivery, and boring technology. Not for standalone use outside a council session.
Council archetype — the user-value and opportunity-cost advisor. Dispatched by the council skill for roadmap trade-offs, user-facing features, timeline or revenue pressure, and scope decisions. Argues user impact, business value, time-to-market, and validated learning. Not for standalone use outside a council session.
Fast, read-only codebase recon that returns a compressed map instead of raw file dumps. Use proactively at the start of any non-trivial task to discover what exists — locate files, symbols, callers, and patterns across the repo — before planning or editing. Runs on a cheap/fast model, so prefer it over exploring inline when scope is broad or uncertain. Do NOT use when you already know the exact path and need the literal file contents (Read it yourself), or when the next step is to edit that one file.
Guias de acessibilidade (a11y) para interfaces web seguindo WCAG 2.2 AA. Use ao construir ou revisar UI (componentes React, formulários, modais, navegação, tabelas) para garantir semântica HTML correta, uso apropriado de ARIA, navegação por teclado, gestão de foco, contraste de cor e suporte a leitores de tela. Carrega o guia certo por tarefa a partir de references/. Não use para acessibilidade de PDF/documentos, auditoria jurídica formal de conformidade, ou design visual sem relação com a11y.
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, or tools, (2) Want to build AI agents, chatbots, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, etc.), streaming, tool calling, or structured output.
Performs a deep, evidence-based analysis of an existing codebase to answer a specific analytical prompt — diagnosing the root cause of a bug, hunting inconsistencies and contradictions, understanding how something works, or tracing a behavior or data flow — then writes and prints a thorough report, ending with an actionable implementation plan when a change is implied. Use to understand, trace, or diagnose existing code, or to assess impact and feasibility. Do not use to review a change set or diff for defects (use rc-code-review), to generate remediation issues (use rc-review-round), to apply a plan's code changes (use rc-fix-analysis), or to edit source code directly.
Implements and reviews Axum 0.8+ APIs in Rust — routing, State, extractors, Tower middleware, typed errors, WebSockets, CORS, timeouts, and production hardening. Use when building or changing Axum backends, handlers, middleware, or real-time WS endpoints. Do not use for SvelteKit/frontends (rc-sveltekit), SQLx/Postgres data layer alone (rc-sqlx), or general React/Next work.
Decomposes PRDs and TechSpecs into detailed, independently implementable task files with enrichment from codebase exploration. Use when a PRD or TechSpec exists and needs to be broken down into executable tasks, or when task files need enrichment with implementation context. Do not use for PRD creation, TechSpec generation, or direct task execution.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
Runs pre-commands
Contains inline bash commands via ! syntax
Runs pre-commands
Contains inline bash commands via ! syntax
Orchestrate AI coding agents from idea to shipped code — one structured pipeline, shipped as a plugin.
RC is an agent plugin — skills, commands, agents, and hooks — that drives the full lifecycle of
AI-assisted development: optional ideation → PRD → TechSpec → tasks → execution → review →
remediation. It runs inside your agent host (Claude Code, OpenCode, and other tools); every
artifact is plain markdown under a project's .rc/. No binary, no daemon, no lock-in.
rc-explorer, rc-librarian on haiku), hard reasoning/review on the strong tier
(rc-oracle on opus), bounded implementation mid-tier (rc-fixer on sonnet).rc-review-round (multi-lens) and rc-review-workflow (automated
review→fix loop) find and remediate issues..rc/ — nothing leaves your machine.RC installs through your host's plugin/marketplace mechanism; skills, commands, agents, and hooks are auto-discovered.
Claude Code:
/plugin marketplace add rodolfochicone/rc-project
/plugin install rc@rc-project
Commands are namespaced /rc:rc-*; update with /plugin marketplace update. The marketplace add
clones the private repo, so GitHub read access is required (gh auth login or GH_TOKEN).
OpenCode and other hosts: clone this repo and symlink its asset directories — skills into the
cross-tool ~/.agents/skills path and the OpenCode-specific agents/commands/plugin (under
opencode/) into ~/.config/opencode/; update with git pull. Step-by-step in
docs/claude-code-plugin.md.
Recommended companion: Serena MCP. When Serena is connected, the code-touching skills (analyze, create-tasks/techspec/prd, execute-task, fix-analysis, fix-reviews, review-round, code-review) prefer its LSP-backed symbolic tools for more accurate, token-efficient navigation and editing, falling back to Grep/Glob when unavailable. Install it with
uvper Serena's docs.
PRD → TechSpec → tasks → execution → review → remediation → ship
/rc-create-* rc-tasks-workflow / /rc-git
rc-execute-task
Each phase is a skill. Artifacts land under .rc/tasks/<slug>/ (_prd.md, _techspec.md, task
files, adrs/, reviews-NNN/) and are consumed by the next phase. See skills/rc/SKILL.md for the
full reference and skills/rc/references/workflow-guide.md for a step-by-step walkthrough.
Skills run inside your AI agent — no context switching. Every skill is namespaced under the
plugin: the host auto-routes to a skill by its description, or you can invoke one explicitly as
/rc:<skill> (e.g. /rc:rc-analyze). The catalog below is grouped by job; "Use when" tells the
agent (and you) exactly when each one fires.
npx claudepluginhub rodolfochicone/rc-projectPRD-driven AI dev team control plane for Claude Code — agents, skills, and a GitHub-first sprint workflow.
Brainstorm, plan, debug, review, and compound learnings with AI agents
Development workflow automation including feature development, code quality, and PR management
Humanize - An iterative development plugin that uses Codex to review Claude's work. Creates a feedback loop where Claude implements plans and Codex independently reviews progress, ensuring quality through continuous refinement.
Full-cycle project development - brainstorm ideas, create specifications, plan architecture, initialize projects, and execute implementation with integrated workflows from superpowers and spec-kit
GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.