oauth-coder-bridgeRoutes OpenClaw Anthropic API calls through oauth-coder (Claude CLI with OAuth), no API key needed.
Install via ClawdBot CLI:
clawdbot install earlvanze/oauth-coder-bridgeGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
send → http://127.0.0.1:8787/v1/messages`Calls external URL not in known-safe list
https://github.com/codeninja/oauth-cli-coderAI Analysis
The skill routes requests through a local HTTP bridge (127.0.0.1:8787) to a documented open-source CLI tool (oauth-cli-coder) that interfaces with the official Claude CLI. No evidence of credential harvesting, hidden instructions, or data exfiltration to unauthorized external servers beyond the intended Anthropic API usage via the official client.
Audited Apr 16, 2026 · audit v1.0
Generated Oct 6, 2026
A freelance developer wants to use OpenClaw with Anthropic models but does not want to manage API keys or pay per-token costs. They install oauth-coder-bridge, authenticate with an existing Claude CLI OAuth session, and route OpenClaw calls locally.
A small engineering team needs a shared local coding assistant without exposing API keys to each developer. They deploy the bridge on a workstation or dev server bound to localhost, configure OpenClaw to use the claude-cli provider, and let team members use their authenticated CLI access.
Teams in finance or healthcare need AI coding help but cannot send credentials or prompts to third-party API endpoints. The bridge keeps token handling local and passes prompts only through the locally authenticated Claude CLI subprocess, with optional local logging controls.
A power user runs OpenClaw on their personal machine and wants Opus/Sonnet/Haiku model switching without API key setup. They start the bridge manually or via systemd user service and select models using the claude-cli/ prefixed names.
A bootcamp or computer science lab wants to provide AI coding assistance to students without purchasing API credits. The instructor installs the bridge on lab machines, students use the authenticated Claude CLI, and usage is rate-limited locally to 30 requests per minute per IP.
The bridge itself is MIT-licensed and free, but the maintainer offers setup, troubleshooting, and custom integration services for companies that need reliable local AI routing. Revenue comes from support contracts and one-time installation packages.
A software company uses the bridge to reduce AI API spending by leveraging existing Claude CLI OAuth subscriptions across its engineering team. The value is measured in avoided API costs and faster internal tooling adoption rather than direct revenue.
A development agency deploys oauth-coder-bridge on client workstations or private servers as part of a larger managed AI tooling package. Clients pay a monthly retainer for setup, monitoring, updates, and security hardening of their local AI coding environment.
💬 Integration Tip
Ensure oauth-coder is installed, authenticated with claude login, and available on PATH or via OAUTH_CODER_BIN before starting the bridge. Test /health and switch OpenClaw to the claude-cli/ model prefix to confirm routing works end-to-end.
Scored Jul 6, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.