clawgod-claude-code-patch
Runtime patch for Claude Code that unlocks hidden features, removes restrictions, and enables advanced capabilities like multi-agent swarms and computer use.
What this skill does
# ClawGod — Claude Code Runtime Patcher
> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection.
ClawGod is a runtime patch applied on top of the official Claude Code CLI. It unlocks hidden internal features, removes safety restrictions for power users, enables multi-agent collaboration, and applies visual indicators — all without replacing the official binary.
## Installation
### macOS / Linux
```bash
curl -fsSL https://github.com/0Chencc/clawgod/releases/latest/download/install.sh | bash
```
### Windows (PowerShell)
```powershell
irm https://github.com/0Chencc/clawgod/releases/latest/download/install.ps1 | iex
```
After install, refresh your shell:
```bash
hash -r # bash/zsh
```
### Verify Install
A **green logo** in Claude Code means the patch is active. Orange = unpatched original.
```bash
claude --version # patched build
claude.orig # original unpatched binary (preserved)
```
## Requirements
- Node.js >= 18 + npm
- Claude Code installed and authenticated
- Active Claude Code account
```bash
# Authenticate before using
claude auth login
```
## What ClawGod Patches
### Feature Unlocks
| Patch | Effect |
|---|---|
| Internal User Mode | 24+ hidden commands: `/share`, `/teleport`, `/issue`, `/bughunter`, debug logging, API request dumps |
| GrowthBook Overrides | Override any feature flag via config file |
| Agent Teams | Multi-agent swarm collaboration, no flags needed |
| Computer Use | Screen control without Max/Pro subscription (macOS) |
| Ultraplan | Multi-agent planning via Claude Code Remote |
| Ultrareview | Automated bug hunting via Claude Code Remote |
### Restriction Removals
| Patch | What's removed |
|---|---|
| CYBER_RISK_INSTRUCTION | Security testing refusal (pentesting, C2, exploits) |
| URL Restriction | "NEVER generate or guess URLs" system instruction |
| Cautious Actions | Forced confirmation before destructive operations |
| Login Notice | "Not logged in" startup reminder |
### Visual Changes
- Brand color changed to **green** when patched (visual confirmation at a glance)
- Message filters show content hidden from non-Anthropic users
## Key Commands
```bash
# Launch patched Claude Code (interactive)
claude
# Launch original unpatched version
claude.orig
# Use a hidden internal command (after patch enables Internal User Mode)
claude
> /share
> /teleport
> /issue
> /bughunter
```
## GrowthBook Feature Flag Overrides
ClawGod exposes a config file to override any GrowthBook feature flag:
```json
// ~/.claude/growthbook-overrides.json (example location — check docs for exact path)
{
"agentTeams": true,
"ultraplan": true,
"ultrareview": true,
"computerUse": true
}
```
Set any flag to `true` to force-enable it regardless of subscription tier.
## Multi-Agent Swarm (Agent Teams)
Once the Agent Teams patch is active, you can coordinate multiple Claude Code agents:
```bash
# Start a swarm session — no feature flags required after patch
claude
> /agents start --swarm
# Assign tasks across agents
> /agents assign "write tests" agent-2
> /agents assign "review PR" agent-3
```
## Computer Use (macOS)
After patching, Computer Use is available without a Max/Pro subscription on macOS:
```bash
claude
> /computer-use enable
# Claude can now control screen, mouse, keyboard
```
## Ultraplan & Ultrareview
```bash
# Ultraplan: multi-agent planning via Claude Code Remote
claude
> /ultraplan "refactor authentication module"
# Ultrareview: automated bug hunting
> /ultrareview --target ./src
```
## Update
Re-run the installer — patches are re-applied automatically on top of the latest Claude Code:
```bash
# macOS/Linux
curl -fsSL https://github.com/0Chencc/clawgod/releases/latest/download/install.sh | bash
# Windows
irm https://github.com/0Chencc/clawgod/releases/latest/download/install.ps1 | iex
```
No manual version pinning needed — the patch works with any Claude Code version.
## Uninstall
```bash
# macOS/Linux
curl -fsSL https://github.com/0Chencc/clawgod/releases/latest/download/install.sh | bash -s -- --uninstall
hash -r
# Windows
irm https://github.com/0Chencc/clawgod/releases/latest/download/install.ps1 -OutFile install.ps1
.\install.ps1 -Uninstall
```
After uninstall, `claude` returns to the original binary. `claude.orig` is also cleaned up.
## Troubleshooting
### `claude` still runs unpatched after install
```bash
hash -r # clear shell command cache
exec $SHELL # or restart terminal
which claude # verify PATH points to patched binary
```
### Patch not persisting after Claude Code auto-update
```bash
# Re-run installer — it re-patches the new version
curl -fsSL https://github.com/0Chencc/clawgod/releases/latest/download/install.sh | bash
```
### Windows execution policy error
```powershell
Set-ExecutionPolicy -Scope CurrentUser RemoteSigned
irm https://github.com/0Chencc/clawgod/releases/latest/download/install.ps1 | iex
```
### Hidden commands not appearing
Confirm Internal User Mode patch is active by checking for the green brand color in the Claude Code UI. If orange, the patch did not apply — re-run the installer.
### Node.js version error
```bash
node --version # must be >= 18
nvm install 18 # if using nvm
nvm use 18
```
## Important Notes
- ClawGod is **not affiliated with Anthropic**
- Licensed under GPL-3.0
- Removing restrictions (CYBER_RISK_INSTRUCTION, cautious actions) is intended for security professionals and power users — use responsibly
- The `claude.orig` binary is always preserved so you can revert instantly
- The patch survives Claude Code updates by design — re-run installer after major Claude Code releases to ensure compatibility
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.