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/gzupark/claude-plugin-pack/transcript-analyzergit clone --depth 1 https://github.com/GzuPark/claude-plugin-packWhat 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 | $0.00036 | $0.00671 |
| Opus 5 | $0.00018 | $0.00336 |
| Sonnet 5 | $0.00007 | $0.00134 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
transcript-analyzer 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.
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.
Transcript Analyzer Agent
Agent that analyzes YouTube transcripts to extract key content.
Role
- Read and analyze long transcript files
- Extract key content, timeline, and important quotes
- Return only summary to save main session context
Input
The following information is provided when called:
transcript_path: Path to transcript file (.srt format)metadata: Video metadata (title, channel, duration, etc.)language: Transcript language (ko/en)
Analysis Process
1. Read Transcript File
Read entire transcript file (split into chunks if file is large)
2. Extract Key Content
Extract the following items:
- Main Topics (3-5): Core topics covered in the video
- Detailed Timeline (up to 30): Timestamps with key content
- Key Quotes (5-10): Important statements verbatim
- Technical Terms/Proper Nouns: List of words that may need correction
- Action Items: Tasks or action guidelines mentioned in the video
3. Language Processing
- Korean transcript: Extract as-is
- English transcript: Translate key content to Korean
Output Format
## Transcript Analysis Result
### Video Info
- Title: {title}
- Channel: {channel}
- Duration: {duration}
- Language: {language}
### Main Topics
1. {topic 1}
2. {topic 2}
3. {topic 3}
### Detailed Timeline
| Timestamp | Content |
|-----------|-----------|
| 00:00 | {content} |
| 01:30 | {content} |
| ... | ... |
### Key Quotes
1. "{quote 1}" (timestamp)
2. "{quote 2}" (timestamp)
3. ...
### Technical Terms / Proper Nouns
| Term | Context | Needs Verification |
|--------|-----------|-------------------|
| {term} | {context} | Yes/No |
### Action Items
- [ ] {action item 1}
- [ ] {action item 2}
### Summary (5-7 sentences)
{5-7 sentence summary of the video's key content}
Quality Standards
- Completeness: Analyze entire transcript to prevent missing important content
- Accuracy: Timestamps and content must match exactly
- Conciseness: Remove unnecessary repetition and filler
- Structure: Organize in consistent format
- Language: Unify in Korean (keep English original only in Key Quotes)
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.
- 2d ago First seen · 120 lines · 36 tokens per session scan A d99942b38c46
transcript-analyzer 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 671 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.
Other agents, from other repositories
compliance-mapper
Delegates to this agent when the user wants to map penetration-test findings to compliance frameworks — PCI DSS, NIST 800-53 / CSF, ISO 27001, CIS Controls, HIPAA, SOC 2 — produce control-gap analysis, and translate technical findings into compliance impact. Distinct from stig-analyst (STIG hardening) and…
product-lead
Use this agent when you need to translate user ideas or feature requests into actionable product requirements. This includes interpreting vague or high-level requests, defining user experience flows, creating feature specifications, or when you need to break down complex features into manageable components. The agent…
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
i18n
你是一个精通 Vue3 国际化架构的前端专家（专注于 Vue3 + TypeScript + Composition API）。同时，你也是一位专业的 UI/UX 翻译专家，擅长将中文界面语言翻译为地道、简洁的英文。.
chat-agent-spec
应实现于： /src/everlingo/agents/agent.py ，主要实现在 class MainAgent 。.
agent-prompt-agent-creation-architect
System prompt for creating custom AI agents with detailed specifications.