No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by leohenon · Agent Tool · ★ 93
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is pi-anthropic-oauth safe to install? View the security audit →
pi-anthropic-oauth Use Claude Pro/Max in Pi with browser OAuth. Features Claude Pro/Max login from Automatic token refresh Claude Code-compatible OAuth headers and prompt shaping No Anthropic API key needed Uses Pi's Anthropic model registry Adds Claude Opus 4.8 and Claude Fable 5 by default Auto-creates → symlink when missing Quick start Start Pi, then run Pi's login command: Choose: Complete the browser login. After login, select an Anthropic model in Pi. When the extension is active, includes and Anthropic models show after OAuth login. Update with: [!NOTE] Anthropic auth changes are closely monitored for quick compatibility updates. System prompt rewriting When using Claude Pro/Max OAuth, the extension prepends Claude Code identity text and rewrites standalone / references in Pi's system prompt to . The rewrite mode defaults to : Other modes are opt-in and avoid rewriting some technical strings such as paths, package names, or repository names. If OAuth starts fail
| Stars | 93 |
| Forks | 22 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 71.2602118366983/100 |
| Open Issues | 4 |
| Last Updated | 2026-09-18 |
| Created | 2026-04-09 |
| Platforms | claude-code, node |
| Est. Tokens | ~15k |
These tools work well together with pi-anthropic-oauth for enhanced workflows:
Looking for a pi-anthropic-oauth alternative? If you're comparing pi-anthropic-oauth with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Extensions, skills, prompts, themes, and developer tools for the Pi coding agent.
Report issues related to MCP integration with Claude here.
Giving Claude ability to run code with E2B via MCP (Model Context Protocol)
Pasal.id - The first open, AI-native Indonesian legal platform. MCP server + web app giving Claude grounded ac
Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, Git
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Explore other popular agent tool tools:
pi-anthropic-oauth is Pi extension for Anthropic OAuth with Claude Pro/Max.. It is categorized as a Agent Tool with 93 GitHub stars.
pi-anthropic-oauth is primarily written in TypeScript. It covers topics such as anthropic, claude, pi.
You can find installation instructions and usage details in the pi-anthropic-oauth GitHub repository at github.com/leohenon/pi-anthropic-oauth. The project has 93 stars and 22 forks, indicating an active community.
pi-anthropic-oauth is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to pi-anthropic-oauth on Agent Skills Hub include pi-coding-agent-forge, claude-ai-mcp, mcp-server. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: