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 lexler/skill-factory --skill demo-with-narrationgit clone --depth 1 https://github.com/lexler/skill-factoryWrote 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/lexler/skill-factory/demo-with-narration)<a href="https://agentmods.dev/skills/lexler/skill-factory/demo-with-narration"><img src="https://agentmods.dev/badge/skills/lexler/skill-factory/demo-with-narration/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/lexler/skill-factory/demo-with-narration"><img src="https://agentmods.dev/badge/skills/lexler/skill-factory/demo-with-narration.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 | $0.00053 | $0.00608 |
| Opus 5 | $0.00026 | $0.00304 |
| Sonnet 5 | $0.00011 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
demo-with-narration 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 13d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demo With Narration
STARTER_CHARACTER = 🎬
A demo is a proof performed twice: once fast and private to convince yourself, once slow and narrated to convince the person watching.
Stage 1: Self-demo
Exercise the real artifact the way its consumer will — the built binary, the running app. A green test suite is the starting point, not the proof.
- Check every behavior you intend to claim: the happy path, each refusal path with its exact stderr reason and exit code, every way the session can end.
- Probe at least one path beyond the obvious ones (quit from the menu, not just close the window) — the extra path is where green-suite bugs hide.
- A detached GUI launch loses its exit status: wrap the launch in a subshell that writes
$?to a file, read the file after the window closes. - Confirm a window really rendered with a screenshot; drive close and quit through accessibility clicks.
Done when every behavior you will claim in the walkthrough has been observed working, and any bug found is fixed and re-proven.
Stage 2: Narrated walkthrough
Replay the proof slowly. The person asked to follow along, so pace for their eyes and ears.
- Announce each step by voice (
speak) before acting: what is about to happen, what to watch for. Pause a beat so the voice finishes before the action starts. - One step per command, numbered. Each step proves exactly one claim.
- When something appears on screen, say how long it will stay and leave it there — ten seconds for a window is enough to actually look at it.
- After each step, one or two sentences of text recapping what was just proven.
- Order the steps as an argument: the input artifact first, then the refusal paths with their exit codes, then the happy path, then every way the session can end.
- Include at least one step that can only pass if the whole pipeline works — a validation error from the deepest layer surfacing at the outermost one — rather than only surface behaviors.
Done when every step was announced before it ran, each claim from the self-demo appeared in exactly one step, and a final recap lists every step.
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.
- 13d ago First seen · 43 lines · 53 tokens per session scan A 97f715962275
demo-with-narration is a skill published in the GitHub repository lexler/skill-factory (234 stars, last pushed 17d ago), licensed Apache-2.0. It adds 53 tokens to every session and 608 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.