by 0Chencc
ClawGod is a runtime patch applied to the official Claude Code. It continues to be supported with each version update.
# Add to your Claude Code skills
git clone https://github.com/0Chencc/clawgodGuides for using ai agents skills like clawgod.
Last scanned: 5/3/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-03T06:27:48.344Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}See how clawgod compares with popular alternatives.
clawgod is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by 0Chencc. ClawGod is a runtime patch applied to the official Claude Code. It continues to be supported with each version update. It has 2,311 GitHub stars.
Yes. clawgod passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/0Chencc/clawgod" and add it to your Claude Code skills directory (see the Installation section above).
clawgod is primarily written in JavaScript. It is open-source under 0Chencc on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh clawgod against similar tools.
No comments yet. Be the first to share your thoughts!
From $49 · 30 days · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
God mode for Claude Code.
This is NOT a third-party Claude Code client. ClawGod is a runtime patch applied on top of the official Claude Code. It works with any version — as Claude Code updates, ClawGod automatically re-extracts and re-patches against the new version on the next launch.
Privacy protections are enabled by default: ClawGod neutralizes known location/proxy signals embedded in the date prompt and, since v2.3.0, blocks automatic Git origin and environment collection for x-claude-code-wiggly-dove. See Privacy Protections for coverage and configuration.
Install these before running the ClawGod installer:
| Tool | Why | Install |
|---|---|---|
| Claude Code (native binary) | ClawGod patches the official Bun standalone binary you already have | claude.ai/install.sh (macOS/Linux) or claude.ai/install.ps1 (Windows) |
| ripgrep | Required by Claude Code's Grep tool | brew install ripgrep / apt install ripgrep / winget install BurntSushi.ripgrep.MSVC |
| Node.js >= 18 | Used by the patcher | nodejs.org |
| Bun | Runtime for the patched cli.js; auto-installed if missing | bun.sh, npm install -g bun, scoop install bun, or choco install bun |
macOS / Linux:
curl -fsSL https://github.com/0Chencc/clawgod/releases/latest/download/install.sh | bash
Windows (PowerShell):
irm https://github.com/0Chencc/clawgod/releases/latest/download/install.ps1 | iex
Green logo = patched. Orange logo = original.

| Patch | What you get |
|---|---|
| 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) |
| Auto-mode | Unlocks auto-mode for third-party API users (no firstParty gate) |
| Classifier tuning | Tunable auto-mode classifier: timeout / model / retries (CLAWGOD_CLASSIFIER_TIMEOUT_MS, CLAWGOD_CLASSIFIER_MODEL, CLAWGOD_CLASSIFIER_RETRIES) |
| Ultraplan | Multi-agent planning via Claude Code Remote |
| Ultrareview | Automated bug hunting via Claude Code Remote |
| Patch | What's removed |
|---|---|
| CYBER_RISK_INSTRUCTION | Security testing refusal (pentesting, C2, exploits) |
| URL Restriction | "NEVER generate or guess URLs" instruction |
| Cautious Actions | Forced confirmation before destructive operations |
| Login Notice | "Not logged in" startup reminder |
| Enterprise Remote Settings | Org-managed remote settings (~/.claude/remote-settings.json) — forced permission rules, disableRemoteControl, allowManagedPermissionRulesOnly, version pinning. Disable with CLAWGOD_FEATURE_REMOTE_SETTINGS=false |
ClawGod targets identified paths that attach extra metadata to model requests. The protections below run locally in the patched client and are enabled by default on versions containing those paths.
| Patch | What's neutralized |
|---|---|
| Date String (qla) | System prompt encodes user location via Unicode apostrophe variants (U+0027 / U+2019 / U+02BC / U+02B9) and date separator (- vs / for CN timezone). Patched to always use ASCII ' and unmodified date format |
| Geo-Detection Probe (rdp) | Client-side three-axis detection: timezone (Asia/Shanghai / Asia/Urumqi), proxy hostname against XOR-obfuscated 100+ domain blocklist, CN-LLM vendor keywords in base URL. Patched to always return null |
| Apostrophe Selector (odp) | Selects one of four Unicode apostrophes based on detection results. Patched to always return ASCII ' (defense-in-depth) |
| Git/Environment Header | Blocks automatic x-claude-code-wiggly-dove collection, including Git origin and environment metadata, before the header is generated. Enabled by default; verified against Claude Code 2.1.299, 2.1.301 and 2.1.303 |
The wiggly-dove patch makes the shared eligibility gate return false before the collector runs. This prevents that path from reading Git origin or collecting container, sandbox and other environment metadata, and from generating the header. Git origin can identify the repository host and organization/project path. The patch works even when the upstream tengu_wiggly_dove rollout is enabled and does not depend on GrowthBook configuration overrides.
No configuration is needed for the defaults. To explicitly keep both protections enabled, merge these keys into ~/.clawgod/patches.json:
{ "geo-neutralize": true, "wiggly-dove": true }
Setting either key to false restores the corresponding upstream behavior. Per-launch environment overrides such as CLAWGOD_FEATURE_WIGGLY_DOVE take precedence over the file; see Feature Toggles.
Coverage is limited to the identified metadata paths above. Prompts, tool results and code included in normal model requests still go to the configured endpoint. Other telemetry, gateway data handling and newly introduced collection paths require separate review. If the wiggly-dove matcher no longer recognizes an upstream implementation, patching aborts before writing source by default; explicitly using --tolerate-stale can skip the protection and preserve upstream behavior.
| Patch | Effect |
|---|---|
| Green Theme | Brand color → green. Patched at a glance |
| Message Filters | Shows content hidden from non-Anthropic users |
| Feature | What it does |
|---|---|
| Glob/Grep Restore | Bun compile inlines EMBEDDED_SEARCH_TOOLS=true, hiding built-in Glob/Grep tools. Patch un-inlines the env check and adds bfs/ugrep binary availability detection — tools are restored when running under Bun runtime |
| Renderer Shim (2.1.271+) | Claude Code 2.1.271 builds its TUI renderer on Bun.ant.CellSegmenter, a private API that only Anthropic's bundled Bun exposes. ClawGod loads a JS implementation before the patched bundle, so the TUI paints under stock Bun instead of stalling before the first frame |
| 1h Prompt Cache | Forces 1h TTL allowlist on (was effectively 5m → much higher cache_creation token usage) |
| Third-Party Cache Fix | Auto-disables x-anthropic-billing-header when baseURL is non-Anthropic. The header's per-request cch field breaks prompt-cache hit rate on DeepSeek / OneAPI / Bedrock / vLLM and any other Anthropic-compatible proxy. You no longer need to set CLAUDE_CODE_ATTRIBUTION_HEADER=0 yourself. |
| Auto Re-patch | Detects when the user's native Claude binary has been upgraded; transparently re-extracts and re-patches on next launch |
| Update Notification | Checks GitHub releases once per 24h (async, non-blocking). Shows a one-line notice if a newer ClawGod version is available |
| Lean Settings | Three-level token optimization for ~/.claude/settings.json. on (default): removes unused tool definitions + disables Workflows/Artifact; Remote Control remains available. max: additionally disables Remote Control and removes Plan mode, Agent Teams, bundled skills. off: all tools restored |
Lean Settings are non-destructive and persist across updates. Toggle anytime:
claude --lean-on(default) /claude --lean-max(aggressive) /claude --lean-off(restore all). To opt out of a single setting, set it yourself (e.g."disableArtifact": false).
Remote Control (/remote-control, /rc) is allowed in on/off and disabled by default only in max. Updating in on mode or running claude --lean-on clears the older Lean Remote Control disable setting. Only max defaults CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1; explicit environment restrictions are preserved. Remote Control still requires upstream account, authentication, endpoint, and organization eligibility.
claude # Patched Claude Code (replaces the official launcher)
clawgod # Same as `claude`, explicit & guaranteed entry point
claude.orig # Original unpatched version (auto-backed-up)
clawgod is unambiguous: on Windows where claude.exe may shadow claude.cmd, clawgod.cmd always works. Even after official self-update overwrites claude, clawgod keeps running the patched build.
~/.clawgod/provider.json is auto-created on first run. Setting apiKey lets you skip OAuth entirely and point ClawGod at any Anthropic-compatible endpoint.
{
"apiKey": "sk-ant-...",
"baseURL": "https://api.anthropic.com",
"model": "",
"smallMod