Qwen Code is an open-source AI coding agent that runs in a terminal and helps developers work with code through language models. It supports multiple model providers and can also be used through IDEs, desktop software, SDKs, and messaging bots.
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.
npx agentmods add skills/qwenlm/qwen-code/prepare-prnpx skills add QwenLM/qwen-code --skill prepare-prgit clone --depth 1 https://github.com/QwenLM/qwen-codeWrote 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/qwenlm/qwen-code/prepare-pr)<a href="https://agentmods.dev/skills/qwenlm/qwen-code/prepare-pr"><img src="https://agentmods.dev/badge/skills/qwenlm/qwen-code/prepare-pr.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00042 | $0.00499 |
| Opus 5 | $0.00021 | $0.00249 |
| Sonnet 5 | $0.00008 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
prepare-pr 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 5d 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.
What it actually says
Prepare PR
Create PR metadata files only. Do not push, comment, or run gh pr create.
Inputs
- Output directory: default
/tmp/autofix - Issue number: from the argument,
ISSUE, or the current branch name
Required Outputs
Write:
<output-dir>/pr-title.txt<output-dir>/pr-body.md
Workflow
- Inspect the current branch diff with
git diff origin/main...HEADand recent commit message withgit log -1 --pretty=%B. - Read
<output-dir>/e2e-report.mdif it exists. - Read
.github/pull_request_template.md. - Write a Conventional Commit style title to
pr-title.txt. - Fill the repository PR template in place and write it to
pr-body.md.
PR Body Rules
- Keep every template section heading exactly as written.
- Do not replace template headings with
Summary,Root Cause,Fix, orTests. - Use prose for motivation and changes; avoid file-by-file implementation notes unless needed for reviewer clarity.
- Include a useful Reviewer Test Plan with concrete behavior to verify.
- Fill
Evidence (Before & After)with concise before/after behavior orN/Afor non-UI changes. - Mark tested OS rows honestly. For Linux-only CI verification, mark Linux tested and macOS/Windows not tested.
- Include risk, out-of-scope, and breaking-change notes.
- Add
Fixes #<issue-number>underLinked Issueswhen an issue number is known. - Keep the
<details><summary>中文说明</summary>section and translate the English body into Chinese there. - Do not hard-wrap paragraphs or list items at a fixed column width.
Common Mistakes
- Writing a free-form PR body instead of filling the template.
- Claiming checks passed when they were not run.
- Omitting the Chinese details section.
- Using closing keywords for unrelated issues.
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.
- 5d ago First seen · 56 lines · 42 tokens per session scan A 9c2e522b1cad
prepare-pr is a skill published in the GitHub repository QwenLM/qwen-code (27,657 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 499 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 2026-08-30.
Other skills, from other repositories
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
agent-manager-reference
Query agent-manager.dev's reference API and MCP server for documentation, the coding CLIs it manages, the tools its MCP server exposes, and the current release. Use instead of scraping the website's HTML.
agent-manager
Run a fleet of AI coding agents as live tmux sessions with agent-manager. Use when a developer is running more than one coding agent, needs to see which one is working or blocked, wants to spawn another on an independent task, or wants to review an agent's diff without leaving the terminal.
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用；包含 AI Coding 事件表语义，以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE，通常与 sls-dashboard-builder 一起使用。.
claude-code-session-broker
Use when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.
arcgentic
Use when the user says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.