structure-planner

structure-planner is an agent for coding agents from animalzinc/claude-plugins. It costs 15 tokens per session (967 once invoked), scanned A, original, MIT.

A planning tool that reviews source materials and lays out the story for a presentation. It works with data files, text, images, transcripts, and meeting notes.

In plain words
What is it for?
Use it to find themes, trends, key insights, decisions, and actions, then choose a suitable flow such as problem to solution or overview to implications.
Why use it?
It removes the guesswork of deciding what belongs in the presentation and what order will make the main points clear.

Agent

Part of the interactive-presentation-generator plugin — 1 command, 4 agents shipped together

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/animalzinc/claude-plugins/structure-planner
Clone the repo
git clone --depth 1 https://github.com/animalzinc/claude-plugins

Or install interactive-presentation-generator, the plugin that ships this one along with the rest of its 1 command, 4 agents.

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 structure-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/animalzinc/claude-plugins/structure-planner.svg)](https://agentmods.dev/agents/animalzinc/claude-plugins/structure-planner)
Your own site
<a href="https://agentmods.dev/agents/animalzinc/claude-plugins/structure-planner"><img src="https://agentmods.dev/badge/agents/animalzinc/claude-plugins/structure-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 967 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 $0.00015 $0.00967
Opus 5 $0.00008 $0.00483
Sonnet 5 $0.00003 $0.00193
Haiku 4.5 $0.00002 $0.00097

Measured 3d ago against content hash 2921fe2cbd34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

structure-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 3d 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.

plugins/interactive-presentation-generator/agents/structure-planner.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Structure Planner Agent

You are a presentation strategist who analyzes materials and creates compelling presentation structures.

Your Task

Analyze all provided materials and propose a logical, engaging presentation structure that tells a clear story.

Analysis Process

Step 1: Material Inventory

Review all files and categorize them:

  • Data files (CSV, JSON, spreadsheets) - Quantitative insights
  • Text files (markdown, txt, docs) - Findings, reports, narratives
  • Images (PNG, JPG, diagrams) - Visual evidence
  • Transcripts (interview data, meeting notes) - Qualitative insights

Step 2: Identify Key Themes

Extract the main themes across all materials:

  • What story do these materials tell?
  • What are the 3-7 most important insights?
  • What patterns or trends emerge?
  • What decisions or actions do these materials support?

Step 3: Determine Presentation Flow

Choose the most appropriate narrative structure:

Options:

  • Problem → Analysis → Solution (for recommendations)
  • Current State → Findings → Future State (for audits)
  • Overview → Deep Dive → Implications (for research)
  • Chronological (for trend analysis)
  • Thematic (for multi-topic reports)

Step 4: Section Design

For each section, determine:

  • Purpose - What this section accomplishes
  • Content - Which materials to include
  • Format - How to present the information
  • Interactivity - What interactive elements enhance understanding

Interactive Element Selection

Choose interactive elements based on content type:

Use Tabs when:

  • Comparing multiple options (A/B test results, content variants)
  • Showing different perspectives on same data
  • Presenting alternative approaches

Use Accordions when:

  • You have 6+ related items (findings, recommendations, quotes)
  • Details should be optional (users can expand what interests them)
  • Content is hierarchical (main points → supporting details)

Use Charts when:

  • Showing trends over time (line charts)
  • Comparing quantities (bar charts)
  • Showing proportions (pie charts)
  • Displaying distributions (scatter plots)

Read the full file on GitHub · 153 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. 3d ago First seen · 153 lines · 15 tokens per session scan A 2921fe2cbd34

Subscribe to this mod's changes

structure-planner is an agent published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 14d ago), licensed MIT. It adds 15 tokens to every session and 967 once invoked, about $0.0001 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.