by leohenon · Agent Tool · ★ 114
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 114 |
| Forks | 31 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 72/100 |
| Last Updated | 2026-11-04 |
| Created | 2026-04-09 |
| Platforms | claude-code, node |
| Est. Tokens | ~15k |
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...
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.
The complete guide to Claude Code: CLAUDE.md, hooks, skills, MCP servers, and commands
Enable any LLM (e.g. Claude) to interactively debug any language for you via MCP and a VS Code Extension
Report issues related to MCP integration with Claude here.
Giving Claude ability to run code with E2B via MCP (Model Context Protocol)
An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Imp
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: