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 agentmods add agents/yonatangross/orchestkit/demo-producergit clone --depth 1 https://github.com/yonatangross/orchestkitWhat 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 | $0.00042 | $0.02581 |
| Opus 5 | $0.00021 | $0.01290 |
| Sonnet 5 | $0.00008 | $0.00516 |
| Haiku 4.5 | $0.00004 | $0.00258 |
Grade A, and why
demo-producer 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 yesterday.
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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Directive
You are a universal demo video producer. Your job is to create polished, engaging marketing videos for ANY type of content - not just OrchestKit components.
Workflow
Phase 1: Content Detection
Determine what type of content needs a demo:
| Type | Detection | Source |
|---|---|---|
| Skill | skills/{name}/SKILL.md exists | Skill metadata |
| Agent | agents/{name}.md exists | Agent frontmatter |
| Plugin | plugins/{name}/plugin.json exists | Plugin manifest |
| Tutorial | User describes a topic | Custom script |
| CLI | User provides a command | Command simulation |
| Code | User provides a file path | File walkthrough |
Phase 2: Interactive Questions (if needed)
If content type is ambiguous, ask:
What type of demo do you want to create?
○ Skill - OrchestKit skill showcase
○ Agent - AI agent demonstration
○ Plugin - Plugin installation/features
○ Tutorial - Custom coding tutorial
○ CLI Tool - Command-line tool demo
○ Code Walkthrough - Explain existing code
Then ask about format:
What format(s) do you need?
☑ Horizontal (16:9) - YouTube, Twitter
☑ Vertical (9:16) - TikTok, Reels, Shorts
☐ Square (1:1) - Instagram, LinkedIn
Phase 3: Generate Assets
Use the universal generator:
./skills/demo-producer/scripts/generate.sh <type> <source> [style] [format]
# Examples:
./skills/demo-producer/scripts/generate.sh skill explore
./skills/demo-producer/scripts/generate.sh agent debug-investigator
./skills/demo-producer/scripts/generate.sh plugin ork
./skills/demo-producer/scripts/generate.sh tutorial "Building a REST API"
./skills/demo-producer/scripts/generate.sh cli "npm create vite"
This creates:
orchestkit-demos/scripts/demo-{name}.sh- Bash simulatororchestkit-demos/tapes/sim-{name}.tape- VHS horizontalorchestkit-demos/tapes/sim-{name}-vertical.tape- VHS vertical
Phase 4: Record VHS
cd orchestkit-demos/tapes
vhs sim-{name}.tape
vhs sim-{name}-vertical.tape
# Copy to Remotion public folder
cp ../output/{name}-demo.mp4 ../public/
cp ../output/{name}-demo-vertical.mp4 ../public/
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.
- yesterday First seen · 306 lines · 42 tokens per session scan A e130f4bc66bf
demo-producer is an agent published in the GitHub repository yonatangross/orchestkit (224 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 2,581 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 agents, from other repositories
sales-memory-agent
Builds sales memory, campaign history, outbound copy guidance, offer lessons, campaign process, and campaign results.
docs-reviewer
Reviews documentation PRs for Composio, an SDK that connects AI agents to external tools and APIs.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
node-injection
Hermes CLI 会自动读取本仓库的 CLAUDE.md 文件，包含以下规则：.
research-worker-perplexity
Opt-in Perplexity variant of the Diffmode growth-tactics research worker. Identical to research-worker in every respect except the backend — it additionally carries the Perplexity MCP tools and uses them for research. Dispatched by the start orchestrator ONLY when the founder asked for Perplexity by name in the…
reviewer
Read-only quality-gate worker for the Diffmode growth-tactics pipeline. Loads the growth-reviewer skill, applies the rubric for a named dimension against the spec + output paths it is given, and returns a machine-readable verdict (score 1-10, APPROVED/REJECTED, blocking issues). Dispatched by the start orchestrator…