claude-tap — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

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 liaohch3 · Codex Skill · ★ 3.1k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is claude-tap safe to install? View the security audit →

Featured in: Agent Governance

About claude-tap

claude-tap 中文文档 is a local proxy and trace viewer for AI coding agents. Run your CLI through it, then inspect the real API traffic: system prompts, conversation history, tool schemas, tool calls, streaming responses, token usage, and request diffs. Website: Local AI Agent Trace Viewer · Guide: How to view agent traces locally It works with Claude Code, Codex CLI, Gemini CLI, Kimi CLI, OpenCode, OpenClaw, [Pi](https://github.com/badlogic/pi-mono/tree/main/packa

agent-debuggingagent-observabilityai-agentsai-toolsapi-debuggingclaude-codecodexcodex-clicursor-clideveloper-tools

Quick Facts

Stars3,092
Forks266
LanguagePython
CategoryCodex Skill
LicenseMIT
Quality Score68.5439507177263/100
Open Issues30
Last Updated2026-08-19
Created2026-02-15
Platformsclaude-code, cli, codex, gemini, python
Est. Tokens~20k

Compatible Skills

These tools work well together with claude-tap for enhanced workflows:

  • tokentap — semantic(0.33)+complementary+same_lang+similar_pop+shared_platform (62%)
  • agent-trace — semantic(0.18)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
  • NadirClaw — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (59%)
  • claude-code-usage-bar — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (59%)
  • Charles-mcp — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)

claude-tap alternative? Top 6 similar tools

Looking for a claude-tap alternative? If you're comparing claude-tap 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.

  • horizon by peters · ⭐ 696

    GPU-accelerated terminal board that puts all your sessions on an infinite canvas

  • agent-of-empires by njbrake · ⭐ 2.4k

    Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports M

  • ai-devkit by codeaholicguy · ⭐ 1.6k

    The control plane for AI coding agents.

  • quint-code by m0n0x41d · ⭐ 1.3k

    Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and p

  • ccmanager by kbwo · ⭐ 1.2k

    Coding Agent Session Manager for Claude Code / Gemini CLI / Codex CLI / Cursor Agent / Copilot CLI / Cline CLI

  • claude-codex-settings by fcakyon · ⭐ 1.1k

    Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is claude-tap?

claude-tap is Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.. It is categorized as a Codex Skill with 3.1k GitHub stars.

What programming language is claude-tap written in?

claude-tap is primarily written in Python. It covers topics such as agent-debugging, agent-observability, ai-agents.

How do I install or use claude-tap?

You can find installation instructions and usage details in the claude-tap GitHub repository at github.com/liaohch3/claude-tap. The project has 3.1k stars and 266 forks, indicating an active community.

What license does claude-tap use?

claude-tap is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to claude-tap?

The top alternatives to claude-tap on Agent Skills Hub include horizon, agent-of-empires, ai-devkit. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

View on GitHub → Browse Codex Skill tools