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 e2e-testinggit 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/e2e-testing)<a href="https://agentmods.dev/skills/qwenlm/qwen-code/e2e-testing"><img src="https://agentmods.dev/badge/skills/qwenlm/qwen-code/e2e-testing/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/e2e-testing"><img src="https://agentmods.dev/badge/skills/qwenlm/qwen-code/e2e-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Excessive Agency · line 30 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00094 | $0.02117 |
| Opus 5.5 | $0.00038 | $0.00847 |
| Sonnet 5.5 | $0.00019 | $0.00423 |
| Haiku 4.5 | $0.00009 | $0.00212 |
Grade A, and why
e2e-testing 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 1mo 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Testing Guide
How to run the Qwen Code CLI end-to-end — from building the bundle to inspecting raw API traffic. Use when unit tests aren't enough and you need to verify behavior through the full pipeline (model API → tool validation → tool execution).
Setup
Which binary to use
- Reproducing bugs: use the globally installed
qwencommand — this matches what the user ran when they filed the issue. - Verifying fixes: build first (
npm run build && npm run bundle), then runnode dist/cli.js— this tests your local changes. - Runtime-only checks (fastest):
npm run dev -- "<prompt>" <flags>— runs TS source via tsx, no build. Usebuild && bundle+node dist/cli.jsonly when the shipped artifact itself matters. (<qwen>below can benpm run dev --.)
Running against a real model
Headless auth comes from ~/.qwen. Force a known-good model with --auth-type +
--model:
<qwen> "your prompt" --auth-type openai --model deepseek-v4-flash \
--approval-mode yolo --output-format json
Gotcha: --model alone won't switch providers — --auth-type (openai/anthropic/qwen-oauth/gemini/vertex-ai) does. Omit it and the run falls back to the default provider and dies
on its missing key.
Isolating runtime artifacts
QWEN_RUNTIME_DIR=<dir> redirects qwen's runtime output — tmp/, debug/,
and projects/<sanitized-cwd>/... (chat recordings, auto-memory, history) —
into <dir> instead of ~/.qwen. Config (settings.json, OAuth tokens,
commands/) still reads from ~/.qwen, so real auth and provider config
work without any setup.
Use when repeated test runs would clutter your real chat history or auto-memory. Skip when the bug you're reproducing depends on the user's actual history or runtime state — that is the repro.
QWEN_RUNTIME_DIR=/tmp/test-1/runtime <qwen> "prompt" ...
Run modes
Headless Mode
Run the CLI non-interactively with JSON output (<qwen> = qwen or
node dist/cli.js per above):
What ships with it
5 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.
- 1mo ago First seen · 240 lines · 94 tokens per session scan A 35430d4c5d72
e2e-testing is a skill published in the GitHub repository QwenLM/qwen-code (28,565 stars, last pushed today), licensed Apache-2.0. It adds 94 tokens to every session and 2,117 once invoked, about $0.0004 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
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.
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…
hatch3r-qa-path
Produces a human-run manual QA test path from a PR, branch diff, or uncommitted working tree — a risk-ordered table of steps, expected results, and automated-coverage references plus a shippability sign-off. Rows are auto-proven via delegated verification sub-agents before emission, so the human walks only what…
hatch3r-a11y-audit
Runs a WCAG AA accessibility audit with findings and fixes across 7 scan categories (keyboard, contrast, ARIA, reduced motion, screen reader, high contrast, automated axe). Use when auditing and remediating accessibility.