qwen-agent

qwen-agent is a skill for Claude Code, Codex from Omar-Obando/qwen-orchestrator. It costs 63 tokens per session (3,417 once invoked), scanned A, original, MIT.

A guide to building software agents with Qwen, a family of AI models. It covers Qwen APIs, model settings, streaming responses, tools, conversation memory, embeddings, and multi-step agent workflows.

In plain words
What is it for?
Use it to integrate Qwen APIs, build tool-using agents, manage conversation history and context windows, add semantic search with embeddings, and configure model responses.
Why use it?
It helps developers connect Qwen models to applications and choose practical patterns for context, knowledge retrieval, tracing, and performance.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to integrate Qwen APIs, build tool-using agents, manage conversation history and context windows, add semantic search with embeddings, and configure model responses.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/omar-obando/qwen-orchestrator/qwen-agent
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.

Any agent
npx skills add Omar-Obando/qwen-orchestrator --skill qwen-agent
Clone the repo
git clone --depth 1 https://github.com/Omar-Obando/qwen-orchestrator

Made for: Claude Code, Codex.

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-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/omar-obando/qwen-orchestrator/qwen-agent/github.svg)](https://agentmods.dev/skills/omar-obando/qwen-orchestrator/qwen-agent)
Your own site
<a href="https://agentmods.dev/skills/omar-obando/qwen-orchestrator/qwen-agent"><img src="https://agentmods.dev/badge/skills/omar-obando/qwen-orchestrator/qwen-agent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for qwen-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/omar-obando/qwen-orchestrator/qwen-agent"><img src="https://agentmods.dev/badge/skills/omar-obando/qwen-orchestrator/qwen-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,417 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00063 $0.03417
Opus 5 $0.00032 $0.01708
Sonnet 5 $0.00013 $0.00683
Haiku 4.5 $0.00006 $0.00342

Measured 8d ago against content hash 54f860443ab8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

qwen-agent 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 8d 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.

skills/qwen-agent/SKILL.md · 512 lines

How it starts

The opening of the file, as written. The whole thing — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Qwen Agent Skill — Qwen Model Integrations & Agent Development

Overview

This skill provides comprehensive guidance for developing Qwen-specific agents, implementing Qwen model integrations, optimizing Qwen performance, and building agent workflows with Qwen models. It includes Qwen API, Qwen-Plus, Qwen-Turbo, and best practices. Based on Qwen official documentation and agent development best practices.

When to Use

Use this skill when:

  • Developing Qwen-specific agents
  • Implementing Qwen model integrations (Qwen-Turbo, Qwen-Plus, Qwen-Max, Qwen-VL)
  • Optimizing Qwen performance and cost management
  • Building agent workflows with Qwen models
  • Using Qwen API endpoints (DashScope API)
  • Configuring Qwen model parameters (temperature, max_tokens, top_p)
  • Implementing Qwen chat completions
  • Setting up Qwen streaming responses
  • Building agents with tools and capabilities
  • Implementing Qwen memory and conversation history
  • Creating Qwen agents with external knowledge sources
  • Building multi-step reasoning with Qwen
  • Using Qwen embeddings for semantic search
  • Implementing Qwen agent tracing with LangSmith
  • Building agents with context window management
  • Creating agents with tool calling capabilities
  • Implementing retry and error handling for Qwen API
  • Setting up rate limiting for Qwen API calls
  • Managing Qwen API costs and usage
  • Building agents with multimodal capabilities (Qwen-VL)

Do NOT use this skill when:

  • Building stateful workflows with complex state (use langgraph skill)
  • Designing database schema (use database-design skill)
  • Creating UI components (use frontend-design skill)
  • Using other LLM providers (use llm-integrations skill)
  • Managing agent teams and coordination (use agent-task-coordinator skill)
  • Building LangChain-based agents (use langchain skill)
  • Implementing complex multi-agent graph architectures (use langgraph skill)

Why avoid: Qwen Agent is specific to Qwen models. For multi-provider support or LangChain integration, use other skills.

Read the full file on GitHub · 512 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 512 lines · 63 tokens per session scan A 54f860443ab8

Subscribe to this mod's changes

qwen-agent is a skill published in the GitHub repository Omar-Obando/qwen-orchestrator (49 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 3,417 once invoked, about $0.0003 per session on Opus 5. 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 2026-09-03.

Related

Other skills, from other repositories

afm

Maintain and extend AFM (maclocal-api), a Swift OpenAI-compatible local LLM server and CLI for Apple Foundation Models, MLX models, API gateway proxying, and Vision OCR. Use when working on AFM CLI commands (afm, afm mlx, afm vision), OpenAI /v1/chat/completions and /v1/models behavior, streaming SSE, tool-calling…

scouzi1966/maclocal-api · 114 tokens

langfuse

Use Langfuse for LLM observability and evaluation and look up Langfuse documentation. In HybridClaw, data access (traces, observations, sessions, scores, prompts, datasets, metrics) goes through the gateway-proxied langfuse.cjs helper with SecretRef auth — reads are green, writes are grant-gated. Documentation…

HybridAIOne/hybridclaw · 111 tokens

llm-wiki

Build and maintain a persistent markdown wiki from raw sources using incremental ingest, indexed pages, and append-only logging.

HybridAIOne/hybridclaw · 27 tokens

distil-pii-redactor

Redact, anonymize, sanitize, or remove PII locally with Distil-PII and llama.cpp; keep personal data and secret values out of model context, logs, and chat.

HybridAIOne/hybridclaw · 46 tokens

llm-pipeline

Use when wiring several LLM calls into a production flow: typed contracts between steps, a router/gateway so 429s, timeouts and outages fail over instead of taking you down, and cost control via caching, model tiers and abort caps. NOT single-prompt wording (that is prompt-engineering), NOT a model-driven tool loop…

ericrisco/rsc-harness · 83 tokens

obtainer

Use this skill when LoopAI needs dataset discovery, acquisition, web-page collection, DataMixer lakehouse operations, data processing, indexing, recipe planning, or production training-data export. In long-running Codex SDK loops, when Analyzer produces an analysis report, failure taxonomy, or user request that…

OpenDCAI/Dataflow-LoopAI · 190 tokens