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/commands/sgaunet/claude-plugins/gen-vhs-demo)<a href="https://agentmods.dev/commands/sgaunet/claude-plugins/gen-vhs-demo"><img src="https://agentmods.dev/badge/commands/sgaunet/claude-plugins/gen-vhs-demo.svg" alt="Measured on agentmods" 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 | $0.04849 |
| Opus 5 | $0.00017 | $0.02424 |
| Sonnet 5 | $0.00007 | $0.00970 |
| Haiku 4.5 | $0.00003 | $0.00485 |
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 8d 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 — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate VHS Demo Command
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 Command 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 command 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.
- 8d ago First seen · 443 lines · 35 tokens per session scan A b4ea619600eb
gen-vhs-demo is a command published in the GitHub repository sgaunet/claude-plugins (16 stars, last pushed 6d ago), licensed MIT. It adds 35 tokens to every session and 4,849 once invoked, about $0.0002 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 commands, from other repositories
docs-setup
Detect ecosystems in this project and write or update the docpin config at .docpin/config.json.
docs-scan
Report which of this project's direct dependencies docpin can resolve version-matched documentation for.
docs
Fetch version-matched documentation for a library used in this project and ground an answer in it (optionally narrowed to a topic).
brand-make
Generate an on-brand asset (logo, social template, doc template, or AI marketing graphic) for the active brand and save it to output/.
brand-new
Create a new visual brand profile via guided Q&A, optionally bootstrapping colors and fonts from an existing website, logo, or brand-guidelines PDF.
brand-setup
Create or update the brand profile that all content generation respects.