agentrigs
+ submit rig
~ / rigs / liaohch3 / claude-tap

liaohch3/claude-tap

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.

↗ GitHub ★ 3,259 mit updated 17d ago project Claude CodeCodex
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~1.9k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit liaohch3/claude-tap/.claude ./rig-claude-tap  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit liaohch3/claude-tap/.agents/skills/codex-e2e-test .claude/skills/codex-e2e-test
$ npx degit liaohch3/claude-tap/.agents/skills/demo-video .claude/skills/demo-video
$ npx degit liaohch3/claude-tap/.agents/skills/e2e-test .claude/skills/e2e-test
$ npx degit liaohch3/claude-tap/.agents/skills/js-in-html-testing .claude/skills/js-in-html-testing
$ npx degit liaohch3/claude-tap/.agents/skills/legibility-check .claude/skills/legibility-check
$ npx degit liaohch3/claude-tap/.agents/skills/playwright-screen-recording .claude/skills/playwright-screen-recording
$ npx degit liaohch3/claude-tap/.agents/skills/pr-preflight .claude/skills/pr-preflight
$ npx degit liaohch3/claude-tap/.agents/skills/push-release .claude/skills/push-release
$ npx degit liaohch3/claude-tap/.agents/skills/real-e2e-test .claude/skills/real-e2e-test
$ npx degit liaohch3/claude-tap/.agents/skills/screenshot-validation .claude/skills/screenshot-validation
$ npx degit liaohch3/claude-tap/.agents/skills/translate-i18n .claude/skills/translate-i18n

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (11)

codex-e2e-testdemo-videoe2e-testjs-in-html-testinglegibility-checkplaywright-screen-recordingpr-preflightpush-releasereal-e2e-testscreenshot-validationtranslate-i18n

Similar rigs

sherparc/Sherpa
Generic AI-harness generator: scan the codebase, plan owner docs, agents and skills, create them after approval.
★ 2 project Claude Code 5 skills 2 agents 4 hooks 16d ago
Automator 2.6k tok ·
spy4x/dotfiles
My AI-agent setup and Linux workstation, as code: one rules source rendered into Claude Code, OpenCode and DSH, plus Deno scripts that install apps and shell.
★ 0 setup Claude CodeCodex 10 skills 1d ago
Skill Collector 8.4k tok ·
maximhq/bifrost
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
★ 8,548 project Claude CodeCodex 15 skills 5d ago
Skill Collector 16.5k tok ·
beixiyo/dotfiles
A lightweight, recoverable, terminal-only workspace for remote development, built around tmux and Neovim / 轻量、可恢复、以 tmux 和 Neovim 为核心的纯终端远程开发工作区
★ 6 setup Claude CodeCodex 7 mcp 33 skills 8 hooks 8d ago
YOLO Cowboy 20.8k tok ·
copied ✓