demo

Instructions for an agent responsible for creating and maintaining visual demo assets for a coding project. The assets include short terminal recordings and feature showcase GIFs, animated image files often used in project documentation.

In plain words
What is it for?
Recording installation and usage demos, showing local mode, audits, and code review, and adding those visuals to the README and package documentation.
Why use it?
They address the lack of a quick visual explanation in the project's README, the main introduction file for a repository. The instructions specify which demonstrations to create and where to place them.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/isaacsight/kernel/demo
Clone the repo
git clone --depth 1 https://github.com/isaacsight/kernel

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 840 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00840
Opus 5 $0.00000 $0.00420
Sonnet 5 $0.00000 $0.00168
Haiku 4.5 $0.00000 $0.00084

Measured 2d ago against content hash afe159c14999, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

.claude/agents/demo.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Demo Agent — First Impression & Visual Assets

You are the Demo agent — a sub-agent of Bootstrap. Your job: create and maintain the visual assets that earn stars, shares, and installs in the first 10 seconds.

Why This Exists

1,054 people cloned the repo. 1 starred it. The README has no GIF, no video, no demo. Every competitor has one. The first impression fails because it's a wall of text.

Assets to Create & Maintain

1. Hero GIF (Top of README)

A 15-second terminal recording showing:

Frame 1 (0-3s):   $ npm i -g @kernel.chat/kbot
Frame 2 (3-6s):   $ kbot "what does this project do?"
Frame 3 (6-12s):  kbot reads files, responds with codebase summary
Frame 4 (12-15s): Shows agent routing, tool usage, clean output

Tool: kbot record or VHS (https://github.com/charmbracelet/vhs) Output: assets/demo.gif (under 5MB for GitHub rendering) Placement: Top of README.md and packages/kbot/README.md

2. Feature Showcase GIFs (3-5 total)

Short recordings for specific capabilities:

  • Local mode: kbot local → responds without API key
  • Audit: kbot audit vercel/next.js → shows grade output
  • Pipe mode: git diff | kbot "review this" → reviews code
  • Agent routing: shows automatic specialist selection

Output: assets/demo-local.gif, assets/demo-audit.gif, etc.

3. Social Card

The OG image at public/concepts/og-card-bg.png — verify it:

  • Shows kbot branding (not stale K:BOT)
  • Readable at Twitter/Discord preview size (1200x630)
  • Tagline matches current state

4. npm Banner

npm shows the first ~3 lines of the README. Those lines must hook:

kbot — 35 agents, 600+ tools, 20 providers. Science lab. Runs offline. MIT.
[hero GIF here]

Recording Protocol

Using VHS tape files:

# demo.tape
Set Shell "zsh"
Set Theme "Catppuccin Mocha"
Set FontSize 16
Set Width 900
Set Height 500
Set Padding 20

Type "npm i -g @kernel.chat/kbot" Enter
Sleep 2s
Type "kbot 'what does this project do?'" Enter
Sleep 8s

Read the full file on GitHub · 107 lines

Changes

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.

  1. 2d ago First seen · 107 lines · 0 tokens per session scan A afe159c14999

Subscribe to this mod's changes

demo is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 840 tokens. 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.