👑 Claude God Mode

The ultimate Claude Code optimization toolkit.
15 AI agents • Autonomous token pipeline • 60-99% token savings • Opus-level reasoning • Elite UI design

Stop burning tokens. Start shipping code.

Claude God Mode is a drop-in optimization toolkit for Claude Code that combines autonomous token reduction with Opus-level reasoning patterns — giving you 2-10x more usage from your plan while producing higher quality code.

⚡ What You Get

Token Pipeline (Autonomous)

Every layer runs automatically — no manual intervention after setup.

hljs language-scss

Your Prompt
    |
    +-  [RTK]               Bash output compressed 60-90%
    |
    +-  [jCodeMunch]         Lightweight code indexing, 95%+ savings (50-150MB)
    |
    +-  [Context Mode]      Tool outputs sandboxed in SQLite (98%)
    |
    +-  [MCP Compressor]    JSON/data auto-compressed (25-66%)
    |
    +-  [Cozempic]          Context auto-pruned at 4 thresholds
    |
    +-  [Headroom]          AST-aware prompt compression (~50%)
    |
    v
Claude sees ONLY what it needs

Quality Agents (On-Demand)

15 specialized agents that push Claude's reasoning to its ceiling.

Agent	What It Does
🔴 `adversarial-coach`	Tries to break your code — finds concrete exploits
🔴 `red-team`	Attacks your stated security assumptions
🟣 `architect`	System design + ADRs, never writes code
🔵 `tree-of-thought`	Explores 3+ approaches before committing
🔵 `constitutional-reviewer`	Multi-pass: write → critique → rewrite → verify (surgical + systematic modes)
🟡 `ensemble-judge`	Picks the best from competing solutions
🟢 `socratic-questioner`	6 mandatory questions before any code
🟢 `hypothesis-tester`	Property-based tests with 1000+ random inputs
🔵 `multi-perspective-reviewer`	4 isolated passes: security, perf, coverage, correctness
🟦 `researcher`	Multi-depth research: `surface` to `overkill`
🟢 `spec-interviewer`	Interviews you before implementation, produces bulletproof SPEC.md
🟣 `ui-architect`	Auto-triggers on frontend tasks. Fetches from component libraries, adds animations
🟣 `design-critic`	Auto-critiques UI after implementation. Scores visual quality 1-10
🟠 `integration-enforcer`	Verifies new code is actually wired into the running system
🟡 `test-authenticator`	Catches fake tests — mock theater, tautologies, happy-path-only

🚀 Quick Start

One-Line Install (Recommended)

macOS / Linux:

hljs language-bash

curl -fsSL https://raw.githubusercontent.com/Itachi-1824/claude-god-mode/main/install.sh | bash

Windows (PowerShell):

hljs language-powershell

irm https://raw.githubusercontent.com/Itachi-1824/claude-god-mode/main/install.ps1 | iex

Manual Install

hljs language-bash

git clone https://github.com/Itachi-1824/claude-god-mode.git
cd claude-god-mode
# Copy agents
cp agents/*.md ~/.claude/agents/
# Copy CLAUDE.md template (review and customize first!)
cp config/CLAUDE.md.template ~/.claude/CLAUDE.md
# Copy .claudeignore template to your projects
cp config/.claudeignore.template /path/to/your/project/.claudeignore

📊 Token Savings

Measured savings from real-world usage:

Layer	Tool	Savings	What It Targets
CLI Output	RTK	60-90%	Bash command output noise
Code Navigation	jCodeMunch	95%+	Lightweight tree-sitter indexing (50-150MB RAM)
Tool Output	Context Mode	98%	Tool output sandboxed, not dumped
Data Compression	MCP Compressor	70-95%	MCP responses compressed + TOON
Context Pruning	Cozempic	30-70%	Stale context auto-cleaned
Input Compression	Headroom	~50%	AST-aware prompt compression
Output Verbosity	Caveman	60-75%	Terse, code-focused responses
Code Navigation	Serena	Significant	LSP-powered symbol navigation
Library Docs	Docfork	Moderate	9000+ library docs on demand
Session Memory	claude-mem	Significant	Persistent cross-session memory + code exploration
Security Analysis	Semgrep	N/A (quality)	5000+ rules, catches security bugs at write-time

Combined effect: 2-10x more usage from the same plan.

🤖 Agents Deep Dive

All agents live in ~/.claude/agents/ and are available globally. Claude auto-delegates to them based on the task, or you can invoke them explicitly.

Adversarial Coach 🔴

hljs language-yaml

Model: Opus | Effort: High | Tools: Read-only

Tries to break your code. Never praises, never approves. Every issue comes with a concrete exploit scenario. Use after any significant implementation.

Red Team 🔴

hljs language-yaml

Model: Opus | Effort: Max | Tools: Read-only

You tell it what security measures you added. It specifically attacks those stated assumptions. Finds blind spots that generic security review misses.

Architect 🟣

hljs language-yaml

Model: Opus | Effort: Max | Tools: Read-only

System design only. Produces ADRs (Architecture Decision Records). Compares 3+ approaches before recommending. Never writes implementation code.

Tree of Thought 🔵

hljs language-yaml

Model: Opus | Effort: Max

Mandatory 4-phase process: Decompose → Branch (min 3 approaches) → Evaluate → Select. Will not start implementing until all branches are compared.

RISE Refiner 🟠

hljs language-yaml

Model: Opus | Effort: High

Recursive self-improvement: Generate → Critique (exactly 3 weaknesses) → Fix only those 3 → Compare before/after. 17-24% measured improvement.

Constitutional Reviewer 🔵

hljs language-yaml

Model: Opus | Effort: High

4-pass review: Write → Critique against 6 principles → Rewrite fixes → Verify all violations resolved. Must find at least 1 issue (if zero found, review wasn't thorough enough).

Researcher 🟦

hljs language-yaml

Model: Sonnet | No turn limit

Multi-depth research with 7 levels: surface, basic, deep, in-depth, ultra, nuclear, overkill. Each level maps to specific search strategies and agent patterns. Supports pluggable web search.

See all agents →

⚙️ What Gets Installed

Component	Location	Purpose
15 agents	`~/.claude/agents/`	Quality + reasoning + UI design patterns
CLAUDE.md	`~/.claude/CLAUDE.md`	Lean config (~60 lines)
Hooks	`~/.claude/settings.json`	Auto-index, auto-prune, graph-first nudge
MCP servers	`~/.claude.json`	Code graph, context sandbox, UI libraries
.claudeignore	Per-project	Prevent reading junk files

Optional Components

The installer asks before installing each of these:

Tool	What	Install
RTK	CLI output compression	`cargo install --git https://github.com/rtk-ai/rtk`
jCodeMunch	Lightweight code indexing	`pip install jcodemunch-mcp`
Context Mode	Tool output sandboxing	`npm install -g context-mode`
MCP Compressor	MCP response compression	`pip install mcp-compressor`
Cozempic	Context auto-pruning	`pip install cozempic`
Headroom	Prompt compression	`pip install "headroom-ai[all]"`
Caveman	Terse output plugin	Via Claude Code plugin marketplace
Serena	LSP code navigation	`uv tool install serena-agent@latest`
Docfork	Library documentation	`npm install -g docfork`
Graphify	Multi-modal code graph	`pip install graphifyy`
Semgrep	Security analysis	Via Claude Code plugin marketplace
claude-mem	Cross-session memory	Via Claude Code plugin marketplace

🎨 UI/Design Stack

God Mode turns Claude into an elite frontend designer with autonomous visual feedback loops.

Component Libraries (MCP Servers)

Server	What You Get
21st.dev Magic	`/ui <description>` → production-ready components
shadcn/ui	Official component registry, zero hallucinations
Magic UI	60+ animated components (beams, particles, meteors)
Animotion	745 CSS animations + 9,000 SVG icons
Dembrandt	Extract design tokens from any website
Aceternity UI	200+ cinematic, 3D, parallax components
Glance	Browser screenshots — Claude sees what it built

Design Agents

Agent	What It Does
`ui-architect`	Auto-triggers on any frontend task. Fetches components from libraries, adds animations, ensures responsive + dark mode
`design-critic`	Auto-triggers after UI implementation. Scores visual quality, catches inconsistencies, suggests polish

How It Works Autonomously

You say "build a landing page for X"
ui-architect agent auto-activates (description-based routing)
It fetches components from 21st.dev/shadcn/magicui instead of writing from scratch
Adds animations from animotion + magicui
design-critic auto-runs after implementation
Visual score + specific fix suggestions returned

Note: 21st.dev requires a free API key from 21st.dev. Replace REPLACE_WITH_YOUR_21STDEV_API_KEY in ~/.claude.json after install.

📦 Per-Project Setup

After installing God Mode globally, each new project needs:

1. Code Index (automatic)

jCodeMunch indexes your project automatically when Claude navigates code via its MCP tools. No manual setup needed.

2. Graphify (one-time per repo)

hljs language-bash

# In your project directory:
graphify .
# Or via Claude:
/graphify .

Auto-updates via PostToolUse hooks.

3. .claudeignore (recommended)

hljs language-bash

# Copy the template to your project root:
cp ~/.claude-god-mode/.claudeignore.template /path/to/project/.claudeignore

Prevents Claude from reading node_modules/, dist/, build artifacts, etc.

🛡️ Safety & Automation

Hook Scripts (`~/.claude/bin/`)

Script	What It Does
`check-orphan.sh`	Detects files with zero import references (advisory)
`require-connected-code.sh`	Blocks "done" if new code has zero callers
`loop-guard.sh`	Escalating guidance on 3+ consecutive identical failures
`session-handover.sh`	Auto-writes HANDOVER.md on session end (git state, decisions, next steps)
`session-resume.sh`	Auto-reads HANDOVER.md on session start for continuity
`status-bar.sh`	Context-usage color bar (green <40%, yellow 40-59%, red 60%+)

Safety Hooks (Deterministic)

Hook	Trigger	Effect
Secret scanner	UserPromptSubmit + Write/Edit	Blocks secrets in prompts and files
Destructive command guard	Bash	Blocks `rm -rf /`, `git reset --hard`, `DROP TABLE`, etc.
`--no-verify` block	Bash(git commit*)	Blocks hook bypass attempts
Branch protection	Bash(git commit*)	Warns on commits to main/master
Orphan detector	Edit	Warns on files with zero references
Connectivity gate	Stop	Blocks completion if code is disconnected
Loop guard	Bash (PostToolUse)	Escalating guidance on stuck loops

🏗️ Architecture

hljs language-scss

~/.claude/
  +-  CLAUDE.md              ~80 lines (lean, connectivity + testing rules)
  +-  settings.json          17 hooks across 8 lifecycle events
  +-  agents/                15 specialized agents (on-demand, 0 tokens when unused)
  +-  bin/                   6 hook scripts (safety, handover, loop guard)
  +-  skills/                Plugin skills (graphify, caveman, etc.)
  +-  plugins/               11 enabled (LSP, security, design, memory, skills)
  +-  projects/              Per-project memory and config

~/.claude.json               12 MCP servers: jcodemunch, context-mode,
                             headroom, serena, docfork, 21st-dev-magic, shadcn,
                             magicui, animotion, dembrandt, aceternity, glance

💬 Philosophy

Autonomous over manual — tools that intercept and optimize automatically beat instructions that Claude might ignore
Agents over CLAUDE.md — specialized agents load on-demand (~0 tokens when unused) vs. CLAUDE.md rules (loaded every turn)
Hooks over suggestions — PreToolUse hooks that nudge behavior are stronger than polite instructions
Evidence over assertions — every verification requires proof (test output, type checker results), not "this should work"
Lean base, rich extensions — CLAUDE.md stays under 60 lines; complexity lives in agents and hooks

🤝 Contributing

PRs welcome! Areas we're looking for help:

New agents for specific domains (ML, mobile, embedded, etc.)
Search provider integrations
Benchmarks comparing with/without God Mode
Platform-specific install improvements
Documentation translations

📝 License

MIT — do whatever you want with it.

_{Built by @Itachi-1824 after hitting Claude Code limits one too many times.}

👑 Claude God Mode

The ultimate Claude Code optimization toolkit.
15 AI agents • Autonomous token pipeline • 60-99% token savings • Opus-level reasoning • Elite UI design

Stop burning tokens. Start shipping code.

⚡ What You Get

Token Pipeline (Autonomous)

Every layer runs automatically — no manual intervention after setup.

hljs language-scss

Your Prompt
    |
    +-  [RTK]               Bash output compressed 60-90%
    |
    +-  [jCodeMunch]         Lightweight code indexing, 95%+ savings (50-150MB)
    |
    +-  [Context Mode]      Tool outputs sandboxed in SQLite (98%)
    |
    +-  [MCP Compressor]    JSON/data auto-compressed (25-66%)
    |
    +-  [Cozempic]          Context auto-pruned at 4 thresholds
    |
    +-  [Headroom]          AST-aware prompt compression (~50%)
    |
    v
Claude sees ONLY what it needs

Quality Agents (On-Demand)

15 specialized agents that push Claude's reasoning to its ceiling.

Agent	What It Does
🔴 `adversarial-coach`	Tries to break your code — finds concrete exploits
🔴 `red-team`	Attacks your stated security assumptions
🟣 `architect`	System design + ADRs, never writes code
🔵 `tree-of-thought`	Explores 3+ approaches before committing
🔵 `constitutional-reviewer`	Multi-pass: write → critique → rewrite → verify (surgical + systematic modes)
🟡 `ensemble-judge`	Picks the best from competing solutions
🟢 `socratic-questioner`	6 mandatory questions before any code
🟢 `hypothesis-tester`	Property-based tests with 1000+ random inputs
🔵 `multi-perspective-reviewer`	4 isolated passes: security, perf, coverage, correctness
🟦 `researcher`	Multi-depth research: `surface` to `overkill`
🟢 `spec-interviewer`	Interviews you before implementation, produces bulletproof SPEC.md
🟣 `ui-architect`	Auto-triggers on frontend tasks. Fetches from component libraries, adds animations
🟣 `design-critic`	Auto-critiques UI after implementation. Scores visual quality 1-10
🟠 `integration-enforcer`	Verifies new code is actually wired into the running system
🟡 `test-authenticator`	Catches fake tests — mock theater, tautologies, happy-path-only

🚀 Quick Start

One-Line Install (Recommended)

macOS / Linux:

hljs language-bash

curl -fsSL https://raw.githubusercontent.com/Itachi-1824/claude-god-mode/main/install.sh | bash

Windows (PowerShell):

hljs language-powershell

irm https://raw.githubusercontent.com/Itachi-1824/claude-god-mode/main/install.ps1 | iex

Manual Install

hljs language-bash

git clone https://github.com/Itachi-1824/claude-god-mode.git
cd claude-god-mode
# Copy agents
cp agents/*.md ~/.claude/agents/
# Copy CLAUDE.md template (review and customize first!)
cp config/CLAUDE.md.template ~/.claude/CLAUDE.md
# Copy .claudeignore template to your projects
cp config/.claudeignore.template /path/to/your/project/.claudeignore

📊 Token Savings

Measured savings from real-world usage:

Layer	Tool	Savings	What It Targets
CLI Output	RTK	60-90%	Bash command output noise
Code Navigation	jCodeMunch	95%+	Lightweight tree-sitter indexing (50-150MB RAM)
Tool Output	Context Mode	98%	Tool output sandboxed, not dumped
Data Compression	MCP Compressor	70-95%	MCP responses compressed + TOON
Context Pruning	Cozempic	30-70%	Stale context auto-cleaned
Input Compression	Headroom	~50%	AST-aware prompt compression
Output Verbosity	Caveman	60-75%	Terse, code-focused responses
Code Navigation	Serena	Significant	LSP-powered symbol navigation
Library Docs	Docfork	Moderate	9000+ library docs on demand
Session Memory	claude-mem	Significant	Persistent cross-session memory + code exploration
Security Analysis	Semgrep	N/A (quality)	5000+ rules, catches security bugs at write-time

Combined effect: 2-10x more usage from the same plan.

🤖 Agents Deep Dive

All agents live in ~/.claude/agents/ and are available globally. Claude auto-delegates to them based on the task, or you can invoke them explicitly.

Adversarial Coach 🔴

hljs language-yaml

Model: Opus | Effort: High | Tools: Read-only

Tries to break your code. Never praises, never approves. Every issue comes with a concrete exploit scenario. Use after any significant implementation.

Red Team 🔴

hljs language-yaml

Model: Opus | Effort: Max | Tools: Read-only

You tell it what security measures you added. It specifically attacks those stated assumptions. Finds blind spots that generic security review misses.

Architect 🟣

hljs language-yaml

Model: Opus | Effort: Max | Tools: Read-only

System design only. Produces ADRs (Architecture Decision Records). Compares 3+ approaches before recommending. Never writes implementation code.

Tree of Thought 🔵

hljs language-yaml

Model: Opus | Effort: Max

Mandatory 4-phase process: Decompose → Branch (min 3 approaches) → Evaluate → Select. Will not start implementing until all branches are compared.

RISE Refiner 🟠

hljs language-yaml

Model: Opus | Effort: High

Recursive self-improvement: Generate → Critique (exactly 3 weaknesses) → Fix only those 3 → Compare before/after. 17-24% measured improvement.

Constitutional Reviewer 🔵

hljs language-yaml

Model: Opus | Effort: High

4-pass review: Write → Critique against 6 principles → Rewrite fixes → Verify all violations resolved. Must find at least 1 issue (if zero found, review wasn't thorough enough).

Researcher 🟦

hljs language-yaml

Model: Sonnet | No turn limit

See all agents →

⚙️ What Gets Installed

Component	Location	Purpose
15 agents	`~/.claude/agents/`	Quality + reasoning + UI design patterns
CLAUDE.md	`~/.claude/CLAUDE.md`	Lean config (~60 lines)
Hooks	`~/.claude/settings.json`	Auto-index, auto-prune, graph-first nudge
MCP servers	`~/.claude.json`	Code graph, context sandbox, UI libraries
.claudeignore	Per-project	Prevent reading junk files

Optional Components

The installer asks before installing each of these:

Tool	What	Install
RTK	CLI output compression	`cargo install --git https://github.com/rtk-ai/rtk`
jCodeMunch	Lightweight code indexing	`pip install jcodemunch-mcp`
Context Mode	Tool output sandboxing	`npm install -g context-mode`
MCP Compressor	MCP response compression	`pip install mcp-compressor`
Cozempic	Context auto-pruning	`pip install cozempic`
Headroom	Prompt compression	`pip install "headroom-ai[all]"`
Caveman	Terse output plugin	Via Claude Code plugin marketplace
Serena	LSP code navigation	`uv tool install serena-agent@latest`
Docfork	Library documentation	`npm install -g docfork`
Graphify	Multi-modal code graph	`pip install graphifyy`
Semgrep	Security analysis	Via Claude Code plugin marketplace
claude-mem	Cross-session memory	Via Claude Code plugin marketplace

🎨 UI/Design Stack

God Mode turns Claude into an elite frontend designer with autonomous visual feedback loops.

Component Libraries (MCP Servers)

Server	What You Get
21st.dev Magic	`/ui <description>` → production-ready components
shadcn/ui	Official component registry, zero hallucinations
Magic UI	60+ animated components (beams, particles, meteors)
Animotion	745 CSS animations + 9,000 SVG icons
Dembrandt	Extract design tokens from any website
Aceternity UI	200+ cinematic, 3D, parallax components
Glance	Browser screenshots — Claude sees what it built

Design Agents

Agent	What It Does
`ui-architect`	Auto-triggers on any frontend task. Fetches components from libraries, adds animations, ensures responsive + dark mode
`design-critic`	Auto-triggers after UI implementation. Scores visual quality, catches inconsistencies, suggests polish

How It Works Autonomously

You say "build a landing page for X"
ui-architect agent auto-activates (description-based routing)
It fetches components from 21st.dev/shadcn/magicui instead of writing from scratch
Adds animations from animotion + magicui
design-critic auto-runs after implementation
Visual score + specific fix suggestions returned

Note: 21st.dev requires a free API key from 21st.dev. Replace REPLACE_WITH_YOUR_21STDEV_API_KEY in ~/.claude.json after install.

📦 Per-Project Setup

After installing God Mode globally, each new project needs:

1. Code Index (automatic)

jCodeMunch indexes your project automatically when Claude navigates code via its MCP tools. No manual setup needed.

2. Graphify (one-time per repo)

hljs language-bash

# In your project directory:
graphify .
# Or via Claude:
/graphify .

Auto-updates via PostToolUse hooks.

3. .claudeignore (recommended)

hljs language-bash

# Copy the template to your project root:
cp ~/.claude-god-mode/.claudeignore.template /path/to/project/.claudeignore

Prevents Claude from reading node_modules/, dist/, build artifacts, etc.

🛡️ Safety & Automation

Hook Scripts (`~/.claude/bin/`)

Script	What It Does
`check-orphan.sh`	Detects files with zero import references (advisory)
`require-connected-code.sh`	Blocks "done" if new code has zero callers
`loop-guard.sh`	Escalating guidance on 3+ consecutive identical failures
`session-handover.sh`	Auto-writes HANDOVER.md on session end (git state, decisions, next steps)
`session-resume.sh`	Auto-reads HANDOVER.md on session start for continuity
`status-bar.sh`	Context-usage color bar (green <40%, yellow 40-59%, red 60%+)

Safety Hooks (Deterministic)

Hook	Trigger	Effect
Secret scanner	UserPromptSubmit + Write/Edit	Blocks secrets in prompts and files
Destructive command guard	Bash	Blocks `rm -rf /`, `git reset --hard`, `DROP TABLE`, etc.
`--no-verify` block	Bash(git commit*)	Blocks hook bypass attempts
Branch protection	Bash(git commit*)	Warns on commits to main/master
Orphan detector	Edit	Warns on files with zero references
Connectivity gate	Stop	Blocks completion if code is disconnected
Loop guard	Bash (PostToolUse)	Escalating guidance on stuck loops

🏗️ Architecture

hljs language-scss

~/.claude/
  +-  CLAUDE.md              ~80 lines (lean, connectivity + testing rules)
  +-  settings.json          17 hooks across 8 lifecycle events
  +-  agents/                15 specialized agents (on-demand, 0 tokens when unused)
  +-  bin/                   6 hook scripts (safety, handover, loop guard)
  +-  skills/                Plugin skills (graphify, caveman, etc.)
  +-  plugins/               11 enabled (LSP, security, design, memory, skills)
  +-  projects/              Per-project memory and config

~/.claude.json               12 MCP servers: jcodemunch, context-mode,
                             headroom, serena, docfork, 21st-dev-magic, shadcn,
                             magicui, animotion, dembrandt, aceternity, glance

💬 Philosophy

Autonomous over manual — tools that intercept and optimize automatically beat instructions that Claude might ignore
Agents over CLAUDE.md — specialized agents load on-demand (~0 tokens when unused) vs. CLAUDE.md rules (loaded every turn)
Hooks over suggestions — PreToolUse hooks that nudge behavior are stronger than polite instructions
Evidence over assertions — every verification requires proof (test output, type checker results), not "this should work"
Lean base, rich extensions — CLAUDE.md stays under 60 lines; complexity lives in agents and hooks

🤝 Contributing

PRs welcome! Areas we're looking for help:

New agents for specific domains (ML, mobile, embedded, etc.)
Search provider integrations
Benchmarks comparing with/without God Mode
Platform-specific install improvements
Documentation translations

📝 License

MIT — do whatever you want with it.

_{Built by @Itachi-1824 after hitting Claude Code limits one too many times.}

claude-god-mode

👑 Claude God Mode

⚡ What You Get

Token Pipeline (Autonomous)

Quality Agents (On-Demand)

🚀 Quick Start

One-Line Install (Recommended)

Manual Install

📊 Token Savings

🤖 Agents Deep Dive

Adversarial Coach 🔴

Red Team 🔴

Architect 🟣

Tree of Thought 🔵

RISE Refiner 🟠

Constitutional Reviewer 🔵

Researcher 🟦

See all agents →

⚙️ What Gets Installed

Optional Components

🎨 UI/Design Stack

Component Libraries (MCP Servers)

Design Agents

How It Works Autonomously

📦 Per-Project Setup

1. Code Index (automatic)

2. Graphify (one-time per repo)

3. .claudeignore (recommended)

🛡️ Safety & Automation

Hook Scripts (~/.claude/bin/)

Safety Hooks (Deterministic)

🏗️ Architecture

💬 Philosophy

🤝 Contributing

📝 License

Similar Packages

claude-god-mode

👑 Claude God Mode

⚡ What You Get

Token Pipeline (Autonomous)

Quality Agents (On-Demand)

🚀 Quick Start

One-Line Install (Recommended)

Manual Install

📊 Token Savings

🤖 Agents Deep Dive

Adversarial Coach 🔴

Red Team 🔴

Architect 🟣

Tree of Thought 🔵

RISE Refiner 🟠

Constitutional Reviewer 🔵

Researcher 🟦

See all agents →

⚙️ What Gets Installed

Optional Components

🎨 UI/Design Stack

Component Libraries (MCP Servers)

Design Agents

How It Works Autonomously

📦 Per-Project Setup

1. Code Index (automatic)

2. Graphify (one-time per repo)

3. .claudeignore (recommended)

🛡️ Safety & Automation

Hook Scripts (~/.claude/bin/)

Safety Hooks (Deterministic)

🏗️ Architecture

💬 Philosophy

🤝 Contributing

📝 License

Similar Packages

Hook Scripts (`~/.claude/bin/`)

Hook Scripts (`~/.claude/bin/`)