Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add sgaunet/claude-plugins/plugin install software-engineeringWrote 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/sgaunet/claude-plugins/gen-vhs-demo)<a href="https://agentmods.dev/skills/sgaunet/claude-plugins/gen-vhs-demo"><img src="https://agentmods.dev/badge/skills/sgaunet/claude-plugins/gen-vhs-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/sgaunet/claude-plugins/gen-vhs-demo"><img src="https://agentmods.dev/badge/skills/sgaunet/claude-plugins/gen-vhs-demo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00035 | $0.04859 |
| Opus 5.5 | $0.00014 | $0.01944 |
| Sonnet 5.5 | $0.00007 | $0.00972 |
| Haiku 4.5 | $0.00003 | $0.00486 |
Grade A, and why
gen-vhs-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 22d 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 — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate VHS Demo
Produce an animated terminal demo of the current project's CLI using
VHS: a .tape script, the rendered .gif, a task
runner entry to regenerate it, a pinned vhs version in mise.toml, and a Demo section in the
README that displays it.
Why This Skill Exists
Problem: A CLI's README is a wall of text. A demo GIF is the single highest-value thing you can add to it, but producing one means learning VHS tape syntax, guessing which commands make a good 40-second story, wiring a regeneration task, pinning the tool, and editing the README - 20-30 minutes per repo. Worse, demo tapes rot silently: flags get deprecated, fixture paths move, and nobody notices until the GIF shows a broken command to every visitor.
Solution: One invocation that:
- Discovers the CLI's real command surface from source, README, and integration tests
- Executes every candidate command and requires exit 0 before it enters the tape, so the GIF cannot show a broken invocation
- Rejects commands that depend on gitignored or untracked fixtures, so the demo reproduces from a clean clone
- Writes the
.tape, renders the.gif, and wirestask demo/ amake demotarget - Pins
vhsinmise.tomlso local and CI renders match - Inserts the
reference into the README at the right heading depth
Content Generation Rules
CRITICAL: When generating any content (tape files, task entries, README sections, or any other output):
- NEVER add Claude Code attribution or co-authorship
- NEVER include phrases like "Generated by Claude", "Created with Claude Code", or similar
- NEVER add "Co-Authored-By: Claude" in commit messages or documentation
- All generated content should appear as if written by a human developer
Additionally, for recorded terminal content:
- NEVER bake real credentials into a tape - no live API keys, tokens, private keys, internal
hostnames, or customer data. Use obviously-fake values (
[email protected]) or generate the material inside aHideblock (openssl rand -hex 32). - NEVER reference a fixture that is gitignored or untracked. The tape must render from a clean clone.
- NEVER use a deprecated flag alias - deprecation warnings end up in the recording.
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.
- 22d ago First seen · 445 lines · 35 tokens per session scan A 4025cf35b722
gen-vhs-demo is a skill published in the GitHub repository sgaunet/claude-plugins (16 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 4,859 once invoked, about $0.0001 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 2026-09-25.
Other skills, from other repositories
metrics-dashboard
Define and design a product metrics dashboard with key metrics, data sources, visualization types, and alert thresholds. Use when creating a metrics dashboard, defining KPIs, setting up product analytics, or building a data monitoring plan.
brainstorm-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.
interview-script
Create a structured customer interview script with JTBD probing questions, warm-up, core exploration, and wrap-up sections. Follows The Mom Test principles — no leading questions, no pitching, focus on past behavior. Use when preparing for user interviews, creating interview guides, or planning discovery research.
ab-test-analysis
Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
outcome-roadmap
Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.