Qwen cli agent

Skill ImL1s/agent-cli-skills/skills/qwen-cli-agent

Run Alibaba Qwen Code CLI headlessly via qwen-exec.sh. Use when the user asks for qwen, Qwen Code, or qwen review / Agent-tool subagents. -r enables sandbox + read-only guard; -T asks for Agent tool / configured subagents. On 429/quota mark BLOCKED — do not retry-loop. Orchestrator owns git (--no-git).From its SKILL.md

Install

npx -y skills add ImL1s/agent-cli-skills --skill qwen-cli-agent

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.5 KB, 357 tokens by cl100k_base, as published. Nobody here has run it

Qwen Code CLI (`qwen`) Executor

When to use

User wants qwen / Qwen Code as the coding agent
Need Qwen /agents, Agent tool parallel launches, or qwen review style workflows from a wrapper

Wrapper

./qwen-exec.sh -C /path/to/repo -t 1800s "Implement phase A. NO git."
./qwen-exec.sh -r -m qwen3.8-max-preview "Review this diff; do not edit."
./qwen-exec.sh -T -f /tmp/bundle.txt

Flags: -m (default qwen3.8-max-preview) · -t · -C · -o text|json|stream-json · -f · -r (sandbox + read-only guard) · -T subagent preamble · --no-git · -- passthrough.

No PTY needed. Text mode extracts final result via lib/parse_stream_json.py. -C is absolutized before use.

Native multi-agent

In-session: /agents create/manage; Agent tool for parallel subagents (.qwen/agents/)
Review pipeline: qwen review … (PR worktree, chunk plan, multi-agent prompts, submit)
-T asks the model to use Agent tool / configured subagents

Discipline

Exit code untrusted. Orchestrator owns git. On 429/quota: BLOCKED stub, no retry loop.

Models

Prefer ids from ~/.qwen/settings.json / qwen --help. Pin explicitly in automation.

What ships with it: 4 files

15.0 KB alongside SKILL.md, 4 of them executable

lib/

common.shruns6.8 KB
parse_stream_json.pyruns3.5 KB
pty_run.pyruns1.7 KB

qwen-exec.shruns2.9 KB

Gives 0 of the 12 instructions most context ai engineering skills give in 357 tokens

Counted across 1,328 of the 2,349 authors here whose files we hold, read 2026-09-06

Dispatch a fresh subagent for each taskin 76 of 1328, across 59 files
Perform spec compliance review before code quality reviewin 44 of 1328, across 34 files
Dispatch a final code reviewer after all tasksin 38 of 1328, across 26 files
Answer subagent questions before allowing implementationin 36 of 1328, across 26 files
Use the least powerful model capable of the taskin 33 of 1328, across 26 files
Create a TodoWrite list for all tasksin 32 of 1328, across 22 files
Perform a task review after each implementationin 31 of 1328, across 24 files
Extract all tasks and context from the planin 29 of 1328, across 20 files
Provide full task text to subagentsin 28 of 1328, across 20 files
Use git worktrees for isolated workspacesin 25 of 1328, across 20 files
Specify the model explicitly when dispatching a subagentin 23 of 1328, across 18 files
Execute all tasks from the plan without stoppingin 21 of 1328, across 16 files

Said here and by no other author read

Use -T to prefer subagents
Use --no-git to prevent unintended commits
Use qwen-exec.sh for Qwen Code tasks
Pin model IDs explicitly
Extract final result from stream json

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.