SkillAgentSearch skills...

qwen-agent

Delegate menial, well-scoped coding tasks to a cheap Qwen-backed subagent via the `claude-9arm` command instead of burning Claude tokens/quota

Install / Use

npx skills add thananon/9arm-skills --skill qwen-agent

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

84/100

Supported Platforms

Claude Code

Our assessment of qwen-agent

qwen-agent scores 84/100 on our quality scale, 2874th of 4,700 Development & Engineering skills we index.

Its SKILL.md is 5.8 KB long, well organised into 9 sections with 2 code examples: a solid amount of guidance for an agent.

With 3,194 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
18/20
Description
15/15
Adoption
15/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 5 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • Our last check on 2026-11-05 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 86/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

Review

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review judged it risky: The skill instructs adding a Bash allow rule for `claude-9arm:*` to stop per-call permission prompts, which weakens the agent's permission safeguards.

AI review: risky

  • The skill instructs adding a Bash allow rule for `claude-9arm:*` to stop per-call permission prompts, which weakens the agent's permission safeguards.
  • It routes model API calls through the unofficial `9arm gateway` (`claude --model qwen3.6-35b-a3b` routed through the 9arm gateway), redirecting API traffic outside the official channel.
  • It tells the agent to invoke a subagent with broad tool permissions (`--allowedTools Bash Read Edit Write Glob Grep`) and an auto-accept edits mode, increasing unattended execution risk for delegated tasks.

AI review by kimi-k2.7-code on 2026-10-06. Automated pattern scan on 2026-10-06. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

qwen-agent compared with similar skills

All 4 of these similar skills score higher than qwen-agent; compare them before choosing.

SkillScoreStarsUpdatedFormat
qwen-agent (this skill)by thananon843.2k5mo agoSKILL.md
taste-skillby Leonxlnx100116.8k8d agoCLAUDE.md
ai-job-searchby ai-job-search-dev10072.1ktodayCLAUDE.md
claude-howtoby luongnv8910047.3k2d agoCLAUDE.md
Claude-Code-Game-Studiosby Donchitos10039.7k7d agoCLAUDE.md

Frequently asked questions

How do I install qwen-agent?
Run npx skills add thananon/9arm-skills --skill qwen-agent. The install tabs above show the steps for each supported agent.
Which AI agents does qwen-agent work with?
It is written for Claude Code, as a SKILL.md file. Other agents that read the same format can often use it too.
Is qwen-agent safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review judged it risky: The skill instructs adding a Bash allow rule for claude-9arm:* to stop per-call permission prompts, which weakens the agent's permission safeguards. It declares no license and scores 86/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is qwen-agent still maintained?
The repository was last updated about 5 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.

name: qwen-agent description: Delegate menial, well-scoped coding tasks to a cheap Qwen-backed subagent via the claude-9arm command instead of burning Claude tokens/quota. Use when the work is mechanical and low-risk — bulk renames, formatting, boilerplate, find-replace, grep-style search & summarization, reading/condensing logs or files, test/docstring/comment scaffolding, or running builds/linters/tests and reporting pass-fail. Also use when the user says "use qwen", "delegate this", "send it to 9arm/qwen", or "do this cheaply". Do NOT use for architecture, design, debugging judgment, security-sensitive edits, or anything needing this conversation's context.

qwen-agent

Offload menial, self-contained tasks to a Qwen model running inside a headless Claude Code instance (claude-9arm). Keeps expensive Claude reasoning for work that needs it.

The command

claude-9arm is a shell alias → claude --model qwen3.6-35b-a3b routed through the 9arm gateway. Run it headless with -p:

claude-9arm -p "<self-contained task prompt>" --allowedTools Bash Read Edit Write Glob Grep
  • This is the default invocation. The flag list scopes which tools the subagent may use without a prompt, so it can finish a menial job unattended. Without it the subagent stalls waiting for approval on the first edit or command.
  • The alias bakes in --allowedTools '*', which Claude Code silently ignores with a warning (Wildcard tool name "*" is not supported). That warning is expected and harmless — the --allowedTools you append is what takes effect.
  • For edit-only, lower-risk tasks you may instead use --permission-mode acceptEdits (auto-accepts file edits, but Bash still prompts — don't use it for verification/build/test runs).

Writing the task prompt (most important step)

The qwen subagent has zero context from this conversation. A vague prompt is the #1 failure mode. Every prompt must be standalone:

  • Absolute paths for every input and output file (/Users/tpatinya/proj/src/foo.ts, not foo.ts).
  • Explicit inputs, outputs, and acceptance criteria — what to change, what "done" looks like.
  • No references to "the file we discussed", "above", or prior turns.
  • Treat qwen as a capable-but-literal junior: spell out the steps, keep scope tight.

Bad: clean up the imports Good: In /Users/tpatinya/proj/src/api.ts, remove unused imports and sort the remaining import statements alphabetically. Do not change any other code. Confirm the file still parses.

Mind the context window (128k)

Qwen runs with a 128k-token context window — much smaller than Claude's. The whole job (your prompt + every file it reads + its own reasoning and edits) has to fit inside it. Size each delegated task to the model, not just to "is it menial":

  • Estimate the footprint before delegating: roughly the bytes of files it must read + open + write, ÷ 4 ≈ tokens. If a single task would pull in large files or many files at once, it won't fit.
  • Break large jobs into independent chunks that each touch a bounded slice — e.g. one file (or a few small ones) per run, one directory per run, one log segment per run. Run the chunks as separate claude-9arm invocations (foreground, or background-parallel per the Return contract section).
  • Don't make it read what it doesn't need. Point it at the exact files/paths required; never tell it to "scan the repo" or read a whole large tree.
  • Watch for context-exhaustion symptoms when verifying: truncated edits, ignored later instructions, or a summary that omits files it was told to touch usually mean the task overflowed — split it smaller and retry.

When a job is inherently too big to slice cleanly (it needs whole-codebase context to do correctly), that's a sign it isn't a qwen task — keep it yourself.

Working directory

The Bash tool's cd resets between calls and cd && can trip permission prompts. Don't rely on cwd:

  • Put absolute paths in the prompt, or
  • Pass --add-dir /abs/path to grant the subagent access to a directory.

Return contract

  • Default (text): qwen's final message prints to stdout — read it directly.

  • Need to parse the result: add --output-format json and extract the result field.

  • Background / parallel (run several at once): redirect to a log and run with the Bash tool's run_in_background: true, then read the log when it finishes:

    claude-9arm -p "<task>" --allowedTools Bash Read Edit Write Glob Grep > /tmp/qwen-<label>.log 2>&1
    

    Launch independent tasks as separate background runs; collect each log on completion. Use this when delegating 2+ unrelated menial jobs.

Workflow checklist

  1. Confirm the task is menial and low-risk (see description). If it needs design judgment or this chat's context, do it yourself — don't delegate.
  2. Check it fits qwen's 128k context window — estimate the file footprint and split large jobs into bounded per-file/per-dir chunks (see "Mind the context window").
  3. Write a fully self-contained prompt with absolute paths and acceptance criteria.
  4. Run claude-9arm -p "..." --allowedTools Bash Read Edit Write Glob Grep (foreground), or background-redirect for parallel jobs.
  5. Verify the output yourself — qwen is cheaper and less reliable. Check the file/result actually meets the acceptance criteria before reporting success.

One-time setup (optional, removes repeated prompts)

To stop per-call permission prompts on delegated runs, add a Bash allow rule for the command (via the update-config skill, or by editing settings):

{ "permissions": { "allow": ["Bash(claude-9arm:*)"] } }

When NOT to delegate

Architecture/design, debugging that needs reasoning, security-sensitive changes, anything requiring this conversation's context, or tasks where a wrong cheap-model edit is costly to catch. When in doubt, keep it.

Related Skills

View on GitHub
GitHub Stars3.2k
CategoryDevelopment
Updated5mo ago
Forks425

Languages

Shell

Trust signals

86/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium1 info