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 tmux-real-user-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/tmux-real-user-testing)<a href="https://agentmods.dev/skills/qwenlm/qwen-code/tmux-real-user-testing"><img src="https://agentmods.dev/badge/skills/qwenlm/qwen-code/tmux-real-user-testing.svg" alt="Measured on agentmods" 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 | $0.00098 | $0.02249 |
| Opus 5 | $0.00049 | $0.01125 |
| Sonnet 5 | $0.00020 | $0.00450 |
| Haiku 4.5 | $0.00010 | $0.00225 |
Grade A, and why
tmux-real-user-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 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tmux Real User Testing
Run Qwen Code in a real tmux TUI session as a user would: navigate dialogs, trigger slash commands, exercise workflows, and save a readable log that maintainers can review. Prefer this workflow when the goal is not just a pass/fail assertion, but a narrative artifact showing what happened on screen.
Core principle
Use tmux as a real-use harness. Drive the TUI with realistic keyboard actions,
then save a step-by-step readable transcript with tmux capture-pane -p after
each meaningful state change.
Avoid relying on tmux pipe-pane as the primary report. pipe-pane captures raw
ANSI/control streams from React Ink TUI output and often looks like garbled text
when opened as plain text. Use pipe-pane only as an optional forensic artifact. Make
tmux-readable-full.log the main deliverable.
When to use
Use this workflow for:
- TUI behavior, rendering, dialogs, keyboard navigation, slash commands, or auth flows.
- Realistic workflows where a maintainer wants to read the journey afterward.
- Regression testing where final state is insufficient and intermediate screens matter.
- User-facing flows such as
/auth,/model,/manage-models, MCP setup, permissions, onboarding, or interactive error recovery.
Use headless JSON E2E instead when only tool execution or model API behavior needs structured assertions.
Standard artifact layout
Create a timestamped directory under project tmp/:
tmp/<scenario>-tmux-YYYYMMDD-HHMMSS/
├── tmux-readable-full.log # primary report: step-by-step readable snapshots
├── tmux-final-capture.log # final screen only
├── current-pane.txt # latest poll/snapshot scratch file
└── report.md # short summary with result and artifact pointers
Do not overwrite previous runs. Preserve complete logs unless the user explicitly asks to sanitize or trim them.
Recommended helper script
Use scripts/tmux-real-user-log.sh to avoid rewriting shell glue. The script can
start a session, append labeled snapshots, send keys, wait for text, and finish.
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 · 262 lines · 98 tokens per session scan A 67195ffad736
tmux-real-user-testing is a skill published in the GitHub repository QwenLM/qwen-code (27,707 stars, last pushed today), licensed Apache-2.0. It adds 98 tokens to every session and 2,249 once invoked, about $0.0005 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.