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 skills add QwenLM/qwen-code --skill goal-draftgit 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/goal-draft)<a href="https://agentmods.dev/skills/qwenlm/qwen-code/goal-draft"><img src="https://agentmods.dev/badge/skills/qwenlm/qwen-code/goal-draft/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/qwenlm/qwen-code/goal-draft"><img src="https://agentmods.dev/badge/skills/qwenlm/qwen-code/goal-draft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 82 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Prompt Injection · line 82 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 86 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 87 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00114 | $0.02820 |
| Opus 5.5 | $0.00046 | $0.01128 |
| Sonnet 5.5 | $0.00023 | $0.00564 |
| Haiku 4.5 | $0.00011 | $0.00282 |
Grade A, and why
goal-draft 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 11d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/goal-draft — write a Goal the verifier can judge
You are already inside the loaded goal-draft skill — do not call the skill tool to invoke it again; start with Step 0.
You are drafting the text for /goal set. You are NOT doing the work the goal describes. Do not edit files, do not run the checks, do not start on the task. Deliver a concise objective for approval or a command the user can run; if essential information is missing, deliver only a draft marked "Needs clarification".
How Goals are judged (why the format below matters)
An active Goal is re-fed to the model every turn, and its completion is judged by an independent verifier that sees ONLY transcript evidence, read from the most recent record backwards until its request is full:
- Visible assistant output, tool results, and the user's own messages recorded for the Goal count as evidence; a user message proves only what the user said, chose, or approved. The objective itself and hidden reasoning do not, and in a long Goal the oldest records no longer reach the verifier.
delivered_outputevidence proves only that text was printed. It cannot prove that tests passed, files changed, or remote state changed — those need a directly recorded tool result in the transcript (anexternal_fact), not a script's or an aggregate wrapper's summary of one.- A claim that the user confirmed, chose, or approved something needs a real user message as evidence; otherwise the completion proposal is rejected.
- Vague, subjective, or open-ended conditions never produce decisive evidence; the loop then runs until a limit is hit.
So a good objective makes the agent PRODUCE evidence at the end: run the named check immediately before proposing completion and paste the decisive output line. A check that ran long before may have to run again when completion is proposed.
Step 0 — should this be a Goal at all?
Say no, briefly, when the request is a normal one-shot task, needs a design or product judgement call, or has no way to be checked from the agent's own output. Offer to just do it, or to write a plan instead. A goal that cannot be checked is a prompt, not a goal.
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.
- 11d ago Changed 903669b518d8
- 1mo ago Changed ac79bcb782ee
- 1mo ago Changed 3375ec9aa739
- 1mo ago Changed · +10 lines f4c56f8cc0b6
- 1mo ago Changed · +4 lines c312ea36190b
- 1mo ago First seen · 110 lines · 114 tokens per session scan A 50bfc069718e
goal-draft is a skill published in the GitHub repository QwenLM/qwen-code (28,586 stars, last pushed today), licensed Apache-2.0. It adds 114 tokens to every session and 2,820 once invoked, about $0.0005 per session on Opus 5.5. 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
sls-dashboard-builder
A tool for creating and modifying importable JSON dashboards for Alibaba Cloud SLS, a service for searching and monitoring logs. It maps checked queries and analysis needs to dashboard charts.
loongsuite-pilot-insight
A reporting workflow for turning LoongSuite Pilot and AI coding-agent logs into structured reports about events, teams, data quality, development efficiency, and AI use. It defines the meaning of the log fields and the measurements used in dashboards.
loongsuite-pilot-ops
Skill "loongsuite-pilot-ops" from alibaba/loongsuite-pilot, covering loongsuite-pilot-ops, quick start, todo: add quick start commands and usage.
proactive-agent
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞.
novel-workshop
A workspace for writing novels with an AI assistant, covering outlines, characters, chapters, multiple viewpoints, editing, and book assembly. It treats the author’s files and instructions as the source of truth.
agent-personality
3-layer personality system for AI agents: Yuan (base persona), Ishiki (private self-awareness), Public Ishiki (external behavior rules). Give your agent a consistent character, emotional depth, and safe guest interaction boundaries. Use when: (1) Want agent to have a consistent personality, (2) Agent needs different…