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 agent-reproduce-aligngit 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/agent-reproduce-align)<a href="https://agentmods.dev/skills/qwenlm/qwen-code/agent-reproduce-align"><img src="https://agentmods.dev/badge/skills/qwenlm/qwen-code/agent-reproduce-align/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/agent-reproduce-align"><img src="https://agentmods.dev/badge/skills/qwenlm/qwen-code/agent-reproduce-align.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- 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 | $0.00062 | $0.00908 |
| Opus 5 | $0.00031 | $0.00454 |
| Sonnet 5 | $0.00012 | $0.00182 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
agent-reproduce-align 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 10d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Reproduce Align
Purpose
Use this skill when Qwen Code already has a candidate implementation and needs evidence-based parity with a selected reference agent: codex or claude-code. The goal is not byte-for-byte equality; it is matching the observable contract that matters for the feature.
Default target repo: the current working directory. Use a user-specified path only when the user explicitly provides one.
Reference Agent Selection
Use the same reference agent selected during $agent-reproduce-feature. If the earlier choice is unavailable, ask once and record the answer in the scenario or run notes.
Workflow
- Re-state the parity target:
- feature name and trigger
- selected reference agent
- one baseline prompt or interaction script
- acceptable differences
- must-match fields
- Run the reference agent and Qwen Code in separate capture directories with the same scenario.
- Capture the selected reference agent's local state before and after the reference run when state may affect parity.
- Normalize traces with
scripts/normalize_trace.py. - Compare normalized traces with
scripts/compare_traces.py. - Inspect differences in this order:
- reference-agent state changes that explain behavior
- missing tool/function names
- schema shape and required fields
- model settings and response mode
- prompt role/order differences that affect behavior
- terminal-visible output and exit status
- Patch Qwen Code, rerun the smallest failing scenario, and repeat.
- Preserve only redacted minimal fixtures in the repo.
Read references/alignment-workflow.md before the first comparison pass.
Common Commands
Normalize:
.qwen/skills/agent-reproduce-align/scripts/normalize_trace.py \
.repro-runs/reference/http.jsonl \
> .repro-runs/reference/normalized.json
Compare:
.qwen/skills/agent-reproduce-align/scripts/compare_traces.py \
.repro-runs/reference/normalized.json \
.repro-runs/qwen/normalized.json
What ships with it
4 files 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.
- 10d ago First seen · 99 lines · 62 tokens per session scan A 1bb5376710ae
agent-reproduce-align is a skill published in the GitHub repository QwenLM/qwen-code (27,718 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 908 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 2026-08-30.
Other skills, from other repositories
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
test-app
Verify a running Mendix app in a browser with Playwright, with OQL for data assertions. Use when asked to test or validate the app end to end, or to confirm that generated pages actually render.
e2e-testing
Use when writing or stabilizing Playwright tests that drive a real browser through multi-step journeys — durable locators, web-first assertions, storageState auth, trace/retries, and flakes that only bite in CI. NOT in-process component tests (that is testing-web), NOT WCAG auditing (that is accessibility), NOT the…
hatch3r-browser-verify
Opt-in browser verification skill — spec-run-first Playwright verification (assertions execute in the runner, agent reads only failures), axe-core a11y audits, toHaveScreenshot() regression diffs, E2E test scaffolds, and snapshot-mode exploratory driving. Default ON for UI-affecting agent invocations; disable globally…
tdd-test-engineer
Use for test-first development, regression tests, flaky test debugging, coverage gaps, test strategy, CI failures, or converting bugs into minimal reproducible tests.