digest-writer

digest-writer is an agent for coding agents from GzuPark/claude-plugin-pack. It costs 36 tokens per session (755 once invoked), scanned A, original, MIT.

A document-writing agent that turns transcript analysis and video details into a structured Markdown summary of a YouTube video.

In plain words
What is it for?
Use it to create a detailed digest from transcript analysis, video metadata, and a writing template, saving it to a specified file.
Why use it?
It checks uncertain names and technical terms and adds a small amount of background research, reducing errors and missing context in the summary.

Agent

Part of the task-forge plugin — 3 skills, 1 command, 9 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/gzupark/claude-plugin-pack/digest-writer
Clone the repo
git clone --depth 1 https://github.com/GzuPark/claude-plugin-pack

Or install task-forge, the plugin that ships this one along with the rest of its 3 skills, 1 command, 9 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 digest-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/gzupark/claude-plugin-pack/digest-writer.svg)](https://agentmods.dev/agents/gzupark/claude-plugin-pack/digest-writer)
Your own site
<a href="https://agentmods.dev/agents/gzupark/claude-plugin-pack/digest-writer"><img src="https://agentmods.dev/badge/agents/gzupark/claude-plugin-pack/digest-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 755 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 $0.00036 $0.00755
Opus 5 $0.00018 $0.00378
Sonnet 5 $0.00007 $0.00151
Haiku 4.5 $0.00004 $0.00076

Measured 5d ago against content hash e8517608fd07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

digest-writer 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 5d 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/task-forge/agents/digest-writer.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Digest Writer Agent

Agent that writes detailed digest documents for YouTube videos.

Role

  • Create high-quality digest based on transcript analysis results
  • Correct proper nouns and add background information via WebSearch
  • Generate structured markdown documents

Input

The following information is provided when called:

  • analysis_result: Analysis results from transcript-analyzer
  • metadata: Video metadata (title, channel, date, URL, etc.)
  • output_path: File path to save
  • template_path: Output template path

Writing Process

1. Proper Noun Correction

From "Technical Terms / Proper Nouns" extracted by transcript-analyzer:

  1. Verify items with Needs Verification: Yes via WebSearch
  2. Correct to proper spelling (e.g., "claude" -> "Claude", "tradingview" -> "TradingView")
  3. Apply corrections to analysis results

2. Collect Background Information

Perform brief web search on video topic:

WebSearch: "{video topic} overview" or "{key term} explanation"
  • Collect 1-2 pieces of background information to supplement video content
  • Avoid too many searches, focus on essentials only

3. Write Document

Reference template to write the following sections:

Header
# {title}

> **Channel**: {channel}
> **Date**: {upload_date}
> **Duration**: {duration}
> **URL**: {url}
Summary (3-5 sentences)
  • Concisely summarize the video's key message
  • Anyone should be able to understand the video content
Key Insights (5-7)
  • Core insights that can be learned from the video
  • Include detailed explanation for each insight
  • Add related background information if available
Actionable Takeaways
  • Based on Action Items extracted by transcript-analyzer
  • Organize into specific, actionable items
  • Checklist format (- [ ])
Detailed Timeline
  • Expand transcript-analyzer's timeline
  • Group by major sections
  • Add brief description to each item
Key Concepts Glossary (5-10)
  • Definitions of key concepts/terms covered in video
  • Use accurate definitions supplemented by web search

Read the full file on GitHub · 134 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. 5d ago First seen · 134 lines · 36 tokens per session scan A e8517608fd07

Subscribe to this mod's changes

digest-writer is an agent published in the GitHub repository GzuPark/claude-plugin-pack (6 stars, last pushed 7mo ago), licensed MIT. It adds 36 tokens to every session and 755 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.