Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/athola/claude-night-marketnpx agentmods add skills/athola/claude-night-market/qwen-delegationWrote 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.
[](https://agentmods.dev/skills/athola/claude-night-market/qwen-delegation)<a href="https://agentmods.dev/skills/athola/claude-night-market/qwen-delegation"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/qwen-delegation/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.
<a href="https://agentmods.dev/skills/athola/claude-night-market/qwen-delegation"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/qwen-delegation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.01191 |
| Opus 5 | $0.00018 | $0.00596 |
| Sonnet 5 | $0.00007 | $0.00238 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
qwen-delegation 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Table of Contents
Qwen CLI Delegation
Overview
This skill implements conjure:delegation-core for the Qwen CLI.
It provides Qwen-specific authentication, quota management,
and command construction.
For shared delegation patterns, see Skill(conjure:delegation-core).
When To Use
- After
Skill(conjure:delegation-core)determines Qwen is suitable - When you need Qwen's large context window (100K+ tokens)
- For batch processing, summarization, or multi-file analysis
- If the
qwenCLI is installed and configured
When NOT To Use
- Choosing which provider to delegate to (use
conjure:delegation-core) - Gemini was the selected provider (use
conjure:gemini-delegation)
Prerequisites
Installation:
# Install Qwen CLI
npm install -g @qwen-code/qwen-code
# Verify installation
qwen --version
# Authenticate: run qwen once and complete the flow it offers
qwen
There is no qwen auth subcommand. qwen --help lists none, and
this file documented three that do not exist: qwen auth status,
qwen auth login and QWEN_API_KEY.
Anything after qwen that is not a recognized flag is delivered to the
model as the prompt, so qwen auth status asked Qwen the question
"auth status" and was billed for it.
Probed on 2026-08-22 it answered
[API Error: 401 Incorrect API key provided] and exited 0, which is
why the delegation registry now declares no auth probe for qwen.
Credentials land in ~/.qwen/oauth_creds.json, which carries its own
expiry_date.
~/.qwen/settings.json exists without credentials, so it is not the
file to test.
The delegator reads the stated expiry and skips qwen without spawning
it, which is what stopped every chain walk paying for a rejected call.
Verification: make -C plugins/conjure delegate-doctor reports
qwen's credential state, including an expiry that has passed.
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.
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.
- 9d ago First seen · 157 lines · 36 tokens per session scan A cf7a3aa3910c
qwen-delegation is a skill published in the GitHub repository athola/claude-night-market (337 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 1,191 once invoked, about $0.0002 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.
Other skills, from other repositories
bailian-managed-agent
A command-line tool for managing Alibaba Cloud Bailian hosted agents and deployments from an agents.yaml file. This file acts as the single description of the remote resources, similar to infrastructure-as-code configuration.
bailian-cli
A command-line hub for Alibaba Cloud Bailian and DashScope resources. It covers applications, models, knowledge bases, usage, authentication, files, MCP services, pipelines, and installing or updating related agent skills.
bailian-protocol
A shared operating guide for Alibaba Cloud Bailian command-line skills. It defines how to choose a provider, request consent, check versions, handle authentication and installation, and report errors.
bailian-kb
A command-line manager for Alibaba Cloud Bailian knowledge bases, which are collections of documents prepared for search and question answering. It handles the stored documents, search services, text chunks, and data-centre files rather than everyday searches.
bailian-gen
An interface to Alibaba Cloud Bailian, a service for generating and understanding images, video, and audio. It supports tasks such as creating images, editing pictures, making videos, text-to-speech, transcription, and asking questions about media.
bailian-web-search
A routing skill for web searches through Alibaba Cloud Bailian. It chooses between Bailian's search service and a model's built-in web-search tool based on the active account and connection.