by CaddyGlow · Codex Skill · ★ 275
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
uvx --with "ccproxy-api[all]" ccproxy serve --port 8000
pipx install "ccproxy-api[all]"Taken from the project's README on GitHub.
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 | 275 |
| Forks | 51 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 70/100 |
| Open Issues | 14 |
| Last Updated | 2026-10-07 |
| Created | 2025-07-04 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~15k |
CCProxy API Server CCProxy is a local, plugin-based reverse proxy that unifies access to multiple AI providers (e.g., Claude SDK/API and OpenAI Codex) behind a consistent API. It ships with bundled plugins for providers, logging, tracing, metrics, analytics, and more.
Looking for a ccproxy-api alternative? If you're comparing ccproxy-api with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, Git
Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolat
LLM orchestration toolkit for agent workflows: planner + workers + synthesis, optional router (LLM + learned
Ship RAG based LLM web apps in seconds.
Run Claude agents in secure cloud sandboxes — via API, CLI, or Slack. One call. Full agent. Zero infrastructur
Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpee
Explore other popular codex skill 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: