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 mendixlabs/mxcli --skill record-narrated-demogit clone --depth 1 https://github.com/mendixlabs/mxcliWrote 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/mendixlabs/mxcli/record-narrated-demo)<a href="https://agentmods.dev/skills/mendixlabs/mxcli/record-narrated-demo"><img src="https://agentmods.dev/badge/skills/mendixlabs/mxcli/record-narrated-demo/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/mendixlabs/mxcli/record-narrated-demo"><img src="https://agentmods.dev/badge/skills/mendixlabs/mxcli/record-narrated-demo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00054 | $0.06953 |
| Opus 5.5 | $0.00022 | $0.02781 |
| Sonnet 5.5 | $0.00011 | $0.01391 |
| Haiku 4.5 | $0.00005 | $0.00695 |
Grade A, and why
record-narrated-demo 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.
How it starts
The opening of the file, as written. The whole thing — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find it fast
sed -n '<from>,<to>p' SKILL.md one section rather than reading the file;
./mxcli syntax <topic> answers how do I write this for a fraction of either.
| lines | section |
|---|---|
| 41-66 | Before recording: the journey must exist and pass |
| 67-85 | Seed the data before you record |
| 86-333 | Recording mechanics |
| 334-411 | The take has to be true, not only watchable |
| 412-432 | What to narrate |
| 433-474 | Where this stops |
| 475-500 | Checklist |
Record a Narrated Demo
Proving a feature works and showing it off are two different jobs, and one script cannot do both well. This skill covers the second. It assumes the first is done.
| Stage 1 — journey | Stage 2 — demo | |
|---|---|---|
| Script | journey-runner.js |
narrated-walkthrough.js |
| Job | asserts | explains |
| Gates the build | yes | no |
| Optimised for | signal — no narration, no reading pauses | a viewer — human pace, on-screen narration |
| Verdict lives here | yes | never |
Both walk the same persona down the same path. The demo reuses the journey's shape and its OQL-backed data checks, so what it shows on screen is still true — but the PASS/FAIL judgment stays in the gating runner. A demo that can fail the build is a test with worse ergonomics; a test that narrates is a demo that misses regressions.
Before recording: the journey must exist and pass
Write journeys/<Module>.journey.json first — one persona, one path, with
carried state, not a list of page stops. Its canonical definition is
skills/journey-proof.md in mxcli-project-toolkit; do not re-derive the
protocol here. In outline, each step asserts five independent rungs:
- Landing guard — the step's
readywidget is visible. Without it every later assertion silently runs against the previous page. - What the screen says —
textPresent/textAbsent. The backend can be correct and the screen can still lie about it. - Ordered spans — the right microflows fired, in order, plus
mustNotFire. - Data effects — row created, association actually set (not null), pointing at the right seeded value. Three claims, not one.
- Outcome — one query over the final state. Per-step deltas can each be right while the net result is wrong.
What ships with it
3 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.
- 5d ago Changed · +16 lines 32f5173c6791
- 1mo ago Changed · +138 lines 4bab04f88b10
- 1mo ago Changed · +32 lines e1135e4736e4
- 1mo ago Changed · +133 lines 167358251f6c
- 1mo ago First seen · 182 lines · 54 tokens per session scan A 4662282e1d10
record-narrated-demo is a skill published in the GitHub repository mendixlabs/mxcli (131 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 6,953 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop.
batch-api
Prepare a many-file, single-turn transform (translate, rewrite, extract) as a plan and submit it to the asynchronous, half-price DashScope Batch API; results are delivered as new files hours later. Invoke explicitly with /batch-api.
workflow-creator
Create or update reusable Dynamic Workflow JavaScript files under .qwen/workflows. Use when the user asks to create, save, edit, or reuse a Dynamic Workflow, including requests started from the Web Shell Workflows page.