_shared_content_synthesis

Shared instructions for turning acquired content from a video transcript, web page, or PDF into structured notes. They organize the material around its main question, smaller topic questions, and supporting evidence.

In plain words
What is it for?
Use it after downloading content with commands such as /youtube-transcript, /scrape-url, or /process-pdf, before saving the resulting knowledge note.
Why use it?
It prevents long source material from becoming an unstructured summary that is difficult to search or use later.

Command

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 commands/witt3rd/claude-plugins/_shared_content_synthesis
Clone the repo
git clone --depth 1 https://github.com/witt3rd/claude-plugins
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 1,748 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 $0.01748
Opus 5 $0.00000 $0.00874
Sonnet 5 $0.00000 $0.00350
Haiku 4.5 $0.00000 $0.00175

Measured 2d ago against content hash 5f049b38c987, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

_shared_content_synthesis 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.

plugins/azkg/commands/_shared_content_synthesis.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shared Content Synthesis Instructions

This file contains common instructions for all content ingestion commands (/youtube-transcript, /scrape-url, /process-pdf). These steps apply AFTER content has been acquired, regardless of source.

Universal Content Processing Pipeline

Phase 1: Question-Oriented Content Synthesis

Apply the methodology from thinking_question_content_synthesis.md:

Step 1: Central Question Discovery

  • Identify the single overarching question the content addresses
  • Consider title, description, opening/closing statements
  • This becomes the note's organizing principle

Step 2: Domain Question Extraction

  • Identify major question domains by analyzing topic transitions
  • Look for transitional phrases: "Now let's talk about," "Another important point," "Moving on to"
  • Group content segments into substantial domain areas

Step 3: Specific and Atomic Question Decomposition

  • Break domain questions into specific questions (section level)
  • Further decompose into atomic questions (evidence level)
  • Extract specific details, examples, data points, and quotes from content

Step 4: Progressive Answer Development

  • Build comprehensive answers using evidence from content
  • Synthesize atomic answers into specific section responses
  • Integrate specific answers to address domain questions
  • Combine domain insights to resolve central question

Phase 2: Note Structure and Metadata

Generate note filename (if not provided):

  • Based on central question or primary topic
  • Use lowercase with underscores
  • Follow naming convention: topic_subtopic.md or moc_topic.md
  • Examples: agents_reasoning_patterns.md, python_async_programming.md

Determine appropriate tags:

  • 3-6 tags mixing dimensions:
    • Technology/Language (#python, #rust, #typescript)
    • Framework/Tool (#mcp, #react)
    • Domain/Discipline (#agents, #llm, #writing)
    • Content Type (#guide, #reference, #pattern)
    • Method/Thinking (#first-principles, #systems-thinking)

Read the full file on GitHub · 222 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 · 222 lines · 0 tokens per session scan A 5f049b38c987

Subscribe to this mod's changes

_shared_content_synthesis is a command published in the GitHub repository witt3rd/claude-plugins (2 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,748 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 2026-08-31.