qwen

qwen is an agent for Claude Code from a5c-ai/babysitter. It costs 0 tokens per session (511 once invoked), scanned A, original, MIT.

An adapter for running Qwen Code, Alibaba's coding command-line tool, from JavaScript. Qwen Code uses the Qwen3-Coder family of models and can connect to an OpenAI-compatible API.

In plain words
What is it for?
Use it to run Qwen coding agents from JavaScript, choose a Qwen3-Coder model, stream generated text, and connect MCP servers.
Why use it?
It lets a program send coding tasks to Qwen Code and receive its output as events, instead of requiring someone to use the command line manually. It does not support plugins, but it can use MCP servers for extensions.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions Gemini CLI.

About the project

Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.

a5c-ai/babysitter · 1,772 stars · on GitHub · a5c.ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/a5c-ai/babysitter/qwen
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for qwen

README.md
[![agentmods](https://agentmods.dev/badge/agents/a5c-ai/babysitter/qwen.svg)](https://agentmods.dev/agents/a5c-ai/babysitter/qwen)
Your own site
<a href="https://agentmods.dev/agents/a5c-ai/babysitter/qwen"><img src="https://agentmods.dev/badge/agents/a5c-ai/babysitter/qwen.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 511 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00511
Opus 5 $0.00000 $0.00255
Sonnet 5 $0.00000 $0.00102
Haiku 4.5 $0.00000 $0.00051

Measured 6d ago against content hash cce2d7526020, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

qwen scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/adapters/reference/agents/qwen.md · 69 lines

What it actually says

Qwen Code

@qwen-code/qwen-code is Alibaba's coding CLI built on top of Gemini CLI, tuned for the Qwen3-Coder family of models. adapters drives it via the qwen binary.

Install

adapters install qwen

Supported on macOS, Linux and Windows.

Authenticate

Qwen Code speaks the OpenAI-compatible API. The quickest path is DashScope:

export OPENAI_API_KEY=sk-...
export OPENAI_BASE_URL=https://dashscope-intl.aliyuncs.com/compatible-mode/v1
export OPENAI_MODEL=qwen3-coder-plus

Alternatively, run qwen interactively and use the built-in OAuth flow.

Example

import { createClient } from '@a5c-ai/adapters';

const client = createClient();
const run = client.run({
  agent: 'qwen',
  model: 'qwen3-coder-plus',
  prompt: 'Summarize the public API in src/index.ts',
});

for await (const ev of run.events()) {
  if (ev.type === 'text_delta') process.stdout.write(ev.delta);
}

Plugins

Plugin support: no. Use MCP servers for extensibility.

MCP Servers

adapters mcp install qwen <mcp-server>
adapters mcp list qwen

Registry: https://modelcontextprotocol.io

Notes

  • Session files live under ~/.qwen/sessions (JSONL).
  • MCP servers are configured under mcpServers in ~/.qwen/settings.json.
  • Capabilities are set conservatively — thinking, JSON mode, and image input default to false pending upstream confirmation.
  • Qwen Code 0.16.2 keeps the npm package unchanged. Upstream adds .qwen/QWEN.local.md project-local context, the memory-leak-debug skill, background-agent concurrency limits, Token Plan cache control, a three-tier auto-compaction ladder, headless runaway-protection guardrails, startup --worktree support, and SDK fixes for canUseTool timeouts and packaged CLI chunks. The graph tracks these as catalog/runtime compatibility metadata; adapters does not yet expose a typed worktree option for Qwen launch.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 69 lines · 0 tokens per session scan A cce2d7526020

Subscribe to this mod's changes

qwen is an agent published in the GitHub repository a5c-ai/babysitter (1,772 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 511 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

rn-code-reviewer

Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…

Lykhoyda/rn-dev-agent · 234 tokens

design-author

Use after research is complete to draft the approach before any code is written. Drafts a 200-line design document covering current state, desired end state, patterns to follow, and decisions made. Resolves its own open questions autonomously, recording each as an explicit, auditable assumption in the design.

bostonaholic/team · 64 tokens

planner

Use after the structure is produced to create the tactical implementation plan. Translates each vertical slice in 7-structure.md into precise file-level steps with acceptance test mappings. The plan is a tactical artifact for the implementer — neither the structure nor the plan is human-reviewed (the design passed…

bostonaholic/team · 64 tokens

security-reviewer

Use when a security review is needed after implementation. Applies OWASP-style checks with fresh context. Critical findings are a hard gate — they block shipping until resolved. Example triggers — "security review", "check for vulnerabilities", "audit this code for security issues".

bostonaholic/team · 56 tokens

technical-writer

Use after implementation to review whether project documentation needs updating. Reads the diff and compares against existing docs to identify gaps and stale content. Produces a structured report — does not rewrite docs itself. Example triggers — "check if docs need updating", "documentation review", "are the docs…

bostonaholic/team · 63 tokens

verifier

Use when comprehensive verification checks need to run before completion. Runs all available checks (format, lint, type check, build, tests) in speed order and produces an evidence-based report. Example triggers — "run all checks", "verify the build", "pre-flight checks", "does everything pass".

bostonaholic/team · 63 tokens