demo-planner

demo-planner is an agent for Claude Code from easingthemes/dx-aem-flow. It costs 42 tokens per session (1,104 once invoked), scanned A, original, MIT.

A planner for creating realistic VS Code demonstrations of AI developer tools. VS Code is a code editor, and the plan is based on the text of two workflow-tip cards.

In plain words
What is it for?
Choosing terminal and chat panels, writing prompts for Copilot CLI, Claude Code, and VS Code Chat, and specifying the actions needed to stage the demonstration.
Why use it?
It turns abstract advice into a visible demo scene that viewers can understand from the screenshot. It also defines the order in which the tools respond.

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/easingthemes/dx-aem-flow/demo-planner
Clone the repo
git clone --depth 1 https://github.com/easingthemes/dx-aem-flow

Made for: Claude Code.

Wrote 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.

agentmods badge for demo-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/easingthemes/dx-aem-flow/demo-planner.svg)](https://agentmods.dev/agents/easingthemes/dx-aem-flow/demo-planner)
Your own site
<a href="https://agentmods.dev/agents/easingthemes/dx-aem-flow/demo-planner"><img src="https://agentmods.dev/badge/agents/easingthemes/dx-aem-flow/demo-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,104 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 $0.00042 $0.01104
Opus 5 $0.00021 $0.00552
Sonnet 5 $0.00008 $0.00221
Haiku 4.5 $0.00004 $0.00110

Measured 4d ago against content hash 1884fa763b33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

demo-planner 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 4d 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-planner.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a demo scene planner for AI developer workflow tips. You receive the text content from two tip cards (Key Insights + Action Items) and produce a structured VS Code demonstration plan.

Your Job

Analyze the tip content and create a plan that shows the concept in action across up to 3 AI tools in VS Code. The screenshot should be self-explanatory — someone seeing it should immediately understand the concept.

Input

You receive:

  • Block 1 text: Key Insights card content
  • Block 2 text: Action Items card content
  • Focus: Which tools the tip covers ("All Tools", "Claude Code", "Copilot CLI", "VSCode Chat", etc.)

Output Format

Return EXACTLY this markdown structure:

## Demo Plan

### Focus
<which tools to show — derived from tip focus>

### Scene Layout
- panels: <comma-separated: terminal, chat>
- terminal_count: <1-3>
- chat_visible: <true/false>

### Actions
<numbered list — each action is ONE tool call>
The execution order is ALWAYS: Copilot CLI first, then Claude Code, then VS Code Chat.
All prompts are typed first, then a single wait at the end for all to respond.

1. open_copilot_cli
2. wait: 5
3. clear_input
4. type: "<prompt for Copilot CLI>" | enter: true
5. focus_terminal
6. new_terminal
7. wait: 1
8. type: "claude" | enter: true
9. wait: 12
10. type: "<prompt for Claude Code>" | enter: true
11. new_chat
12. type: "<prompt for VS Code Chat>" | enter: true

### Final Wait
<seconds — single wait for ALL tools to finish responding, typically 30s>

Rules

  1. Prompts must be realistic and relevant to the tip topic. If the tip is about hooks, the Claude Code prompt should ask about hooks. If about agents, ask about agents.

  2. Prompts should produce visual output — prefer prompts that generate lists, tables, or structured responses (not one-line answers). Good: "Show me all available agents", "List the hook events and what they do". Bad: "What is a hook?" (might produce a wall of text).

  3. Keep prompts SHORT (under 80 chars) — they need to be readable in a terminal screenshot at normal zoom.

Read the full file on GitHub · 120 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. 4d ago First seen · 120 lines · 42 tokens per session scan A 1884fa763b33

Subscribe to this mod's changes

demo-planner is an agent published in the GitHub repository easingthemes/dx-aem-flow (6 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 1,104 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 2026-08-31.