By rivit-studio
Core Claude Code productivity system — agents, auto-delegation, workflows, and best practices
Expert code review with focus on security, performance, and best practices
Debugging specialist for errors, test failures, and unexpected behavior. Use PROACTIVELY when encountering issues.
Plans and architects new features with comprehensive implementation strategy
Analyzes specifications, PRDs, and feature descriptions to extract structured requirements, acceptance criteria, and technical constraints. Use before feature planning when requirements are vague or complex.
Orchestrates agent teams for complex, multi-part work. Delegates tasks, enforces quality gates, and coordinates teammates so nothing falls through the cracks.
Auto-delegation and task prioritization rules for Claude Code. Determines when to use subagents, which agent to delegate to, and how to break down complex tasks. Apply when planning work, starting new tasks, or when a task involves multiple concerns.
Universal Claude Code best practices for any coding task. Covers tool usage patterns, anti-patterns, code review standards, commit conventions, and workflow quality standards. Apply to ALL software engineering tasks.
Assess whether the `.gir/` memory bank is stale and recommend what to update.
Scaffold the `.gir/` memory bank directory in the current project with all 5 template files.
Generate a `CLAUDE-project.md` for the current project by detecting its tech stack and prompting for key configuration values.
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.
A modular Claude Code plugin ecosystem. Install only what you need — curated agents, auto-delegation, memory bank, and domain-specific tooling.
"Doom Song!"
GIR is a modular ecosystem that separates:
Drop into any project for instant Claude Code productivity.
GIR is designed so you only pay the token cost for what you use. Install gir-core, then add only the spokes your project needs. No wasted context, no irrelevant tools loaded into every session.
| Setup | Token Savings vs. Monolithic |
|---|---|
| Core only | ~45% reduction |
| Core + 1 spoke | ~35–40% reduction |
| Core + 2–3 spokes | ~25–35% reduction |
| All 7 modules | Comparable total, but fully modular |
Each module self-registers at session start. Installed modules list their tools in .gir/GIR.modules. Uninstalled modules are invisible — zero token overhead.
GIR uses a hub-and-spoke model. gir-core is required and provides the foundation. Spoke plugins are optional and extend it for specific domains.
┌─────────────────┐
│ gir-core │ ← REQUIRED
│ │
│ agents: │
│ • feature-architect
│ • code-reviewer│
│ • debugger │
│ • team-lead │
│ • spec-analyst │
│ │
│ skills + cmds │
│ hooks + MCP │
└────────┬────────┘
│
┌────────────┬───────────────┼───────────────┬────────────┬────────────┐
│ │ │ │ │ │
┌───▼───┐ ┌────▼────┐ ┌───────▼──────┐ ┌────▼────┐ ┌────▼───┐ ┌────▼───┐
│gir-web│ │gir-auto-│ │ gir-tools │ │gir-data-│ │ gir-ai │ │ gir-qa │
│ │ │ mation │ │ │ │ base │ │ │ │ │
│• docs │ │ │ │ • agenthub │ │ │ │• Gemini│ │• Code- │
│• deploy│ │ • n8n- │ │ • subtask- │ │• Supa- │ │ -CLI │ │ Rabbit│
│• ui- │ │ builder│ │ manager │ │ base │ │• Codex │ │• Jules │
│ gen │ │ │ │ • subtask │ │ tools │ │ │ │ │
│ │ │ │ │ skills │ │ │ │ │ │ │
└───────┘ └─────────┘ └──────────────┘ └─────────┘ └────────┘ └────────┘
GIR is designed for zero wasted context. You only load what you use.
| Setup | Context Used | Token Savings |
|---|---|---|
| Core only | ~7-8K (3.5-4%) | 45% vs. monolithic |
| Core + 1 spoke | ~9-10K (4.5-5%) | 35-40% savings |
| Core + 2-3 spokes | ~11-14K (5-7%) | 25-35% savings |
| All modules | ~19-32K (10-16%) | Full modular ecosystem |
What this means: Installing just gir-core uses less than 4% of your 200K context window, leaving 193K+ tokens for your actual code and tasks. Each additional module adds only 2-4K tokens.
If you need a module, install it. If you don't, it costs nothing.
claude plugin marketplace add rivit-studio/GIR
claude plugin install gir-core
claude plugin install gir-web # Frontend/fullstack (v0, Figma, Vercel)
claude plugin install gir-automation # n8n workflow automation
claude plugin install gir-tools # AgentHub + team coordination
claude plugin install gir-database # Database management (Supabase)
claude plugin install gir-ai # AI delegation (Gemini-CLI, Codex)
claude plugin install gir-qa # QA & review (CodeRabbit, Jules)
/gir-core:modules
claude plugin install gir-core
claude plugin install gir-web # Frontend tooling (v0, Figma, Vercel)
Then run /gir-core:init-project to scaffold CLAUDE-project.md for your stack.
claude plugin install gir-core
Then run /gir-core:init-project to scaffold CLAUDE-project.md for your stack.
Requires gir-core. QA & review tools — CodeRabbit PR reviews and Jules AI delegation for Claude Code
Requires gir-core. Frontend/fullstack agents and design skills for Claude Code
Requires gir-core. n8n workflow builder agent for Claude Code
Requires gir-core. Database management — Supabase MCP tools for Claude Code
Requires gir-core. AI tool delegation — Gemini-CLI, Codex, and other AI integrations for Claude Code
npx claudepluginhub rivit-studio/gir --plugin gir-coreHigh-intelligence Claude Code copilot with deep code reasoning, evidence-driven planning, orchestration-first execution, model routing, context budgeting, CI/CD integration, enterprise security, plugin development, prompt engineering, performance profiling, agent teams, channels (event-driven autonomy with CI webhook, mobile approval relay, Discord bridge, and fakechat dev profile), interactive tutorials, LSP integration, security-hardened hook script library, MCP Prompts coverage, common workflow packs, runtime selection guide, computer-use patterns, checkpointing, scheduled-task blueprints, repo bootstrap scanner, hook policy engine (8 installable packs), layered memory deployment, role-based subagent packs (implementer, debugger, migration-lead, dependency-auditor, release-coordinator), 5 agent-team topology kits, autonomy operating mode (4 profiles + 3 gates), and a queryable 15-tool MCP documentation server with autonomy advisor.
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
Multi-agent orchestrator for Claude Code. Track work with convoys, sling to polecats. The Cognition Engine for AI-powered software factories.
Harness for Claude Code — skills, /harness:* slash commands, persona subagents, lifecycle hooks, and MCP tools without per-repo `harness setup`. Sibling plugins exist for Cursor, Gemini CLI, and Codex.
Unified capability management center for Skills, Agents, and Commands.
Installer for TÂCHES' Get-Shit-Done workflow system - meta-prompting, context engineering and spec-driven development