agentrigs
+ submit rig
~ / rigs / QwenLM / qwen-code

QwenLM/qwen-code

An open-source AI coding agent that lives in your terminal.

↗ GitHub ★ 28.3k apache-2.0 updated 6d ago project Claude CodeCodex
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~5.6k tokens
Moderate · median rig: 2.2k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/QwenLM/qwen-code

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 QwenLM/qwen-code/.qwen/skills/agent-reproduce-align .claude/skills/agent-reproduce-align
$ npx degit QwenLM/qwen-code/.qwen/skills/agent-reproduce-feature .claude/skills/agent-reproduce-feature
$ npx degit QwenLM/qwen-code/.qwen/skills/autofix .claude/skills/autofix
$ npx degit QwenLM/qwen-code/.qwen/skills/bugfix .claude/skills/bugfix
$ npx degit QwenLM/qwen-code/.qwen/skills/ci-flaky-patrol .claude/skills/ci-flaky-patrol
$ npx degit QwenLM/qwen-code/.qwen/skills/codegraph .claude/skills/codegraph
$ npx degit QwenLM/qwen-code/.qwen/skills/create-issue .claude/skills/create-issue
$ npx degit QwenLM/qwen-code/.qwen/skills/deflake .claude/skills/deflake
$ npx degit QwenLM/qwen-code/.qwen/skills/docs-audit-and-refresh .claude/skills/docs-audit-and-refresh
$ npx degit QwenLM/qwen-code/.qwen/skills/docs-update-from-diff .claude/skills/docs-update-from-diff
$ npx degit QwenLM/qwen-code/.qwen/skills/e2e-testing .claude/skills/e2e-testing
$ npx degit QwenLM/qwen-code/.qwen/skills/feat-dev .claude/skills/feat-dev
$ npx degit QwenLM/qwen-code/.qwen/skills/find-simplifications .claude/skills/find-simplifications
$ npx degit QwenLM/qwen-code/.qwen/skills/memory-leak-debug .claude/skills/memory-leak-debug
$ npx degit QwenLM/qwen-code/.qwen/skills/prepare-pr .claude/skills/prepare-pr
$ npx degit QwenLM/qwen-code/.qwen/skills/qwen-code-claw .claude/skills/qwen-code-claw
$ npx degit QwenLM/qwen-code/.qwen/skills/repo-hygiene .claude/skills/repo-hygiene
$ npx degit QwenLM/qwen-code/.qwen/skills/structured-debugging .claude/skills/structured-debugging
$ npx degit QwenLM/qwen-code/.qwen/skills/terminal-capture .claude/skills/terminal-capture
$ npx degit QwenLM/qwen-code/.qwen/skills/tmux-real-user-testing .claude/skills/tmux-real-user-testing
$ npx degit QwenLM/qwen-code/.qwen/skills/triage .claude/skills/triage
$ npx degit QwenLM/qwen-code/.qwen/skills/verify-pr .claude/skills/verify-pr
$ npx degit QwenLM/qwen-<redacted> .claude/skills/synonyms
$ npx degit QwenLM/qwen-code/packages/desktop/.agents/skills/desktop-brand-builder .claude/skills/desktop-brand-builder

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,413 rigs:

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

Skills (24)

agent-reproduce-alignagent-reproduce-featureautofixbugfixci-flaky-patrolcodegraphcreate-issuedeflakedocs-audit-and-refreshdocs-update-from-diffe2e-testingfeat-devfind-simplificationsmemory-leak-debugprepare-prqwen-code-clawrepo-hygienestructured-debuggingterminal-capturetmux-real-user-testingtriageverify-prsynonymsdesktop-brand-builder

Similar rigs

chattymin/PokeTokenBar
Use your tokens to raise, evolve, and collect Pokémon! 🥚
★ 497 project Claude CodeCodex 1 skills 10d ago
Minimalist 1.3k tok ·
bitbonsai/mcpvault
A lightweight Model Context Protocol (MCP) server for safe Obsidian vault access
★ 1,682 project Claude CodeCodex 2 skills 1 hooks 1d ago
Pragmatist 2.6k tok ·
foyzulkarim/claude-lens
A local dashboard for visualizing your Claude Code usage — sessions, token costs, cache performance, tool calls, and daily breakdowns.
★ 250 project Claude CodeCodex 3 skills 2mo ago
Pragmatist 3.9k tok ·
herdrdev/herdr
the runtime your coding agents live on
★ 42.1k project Claude CodeCodex 4 skills 7d ago
Pragmatist 8.1k tok ·
copied ✓