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 skills add LuuOW/meridian-mcp --skill transcript-ingestiongit clone --depth 1 https://github.com/LuuOW/meridian-mcpWrote 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.
[](https://agentmods.dev/skills/luuow/meridian-mcp/transcript-ingestion)<a href="https://agentmods.dev/skills/luuow/meridian-mcp/transcript-ingestion"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/transcript-ingestion/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/luuow/meridian-mcp/transcript-ingestion"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/transcript-ingestion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.00599 |
| Opus 5 | $0.00023 | $0.00300 |
| Sonnet 5 | $0.00009 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
transcript-ingestion 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 7d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
transcript-ingestion
Use this when the task depends on spoken-source fidelity: YouTube episodes, podcast interviews, show transcripts, or transcript-like notes.
Goal
Turn noisy video or podcast pages into transcript-grade text that is usable for retrieval and persona synthesis.
Preferred Order
- Native captions/transcript endpoints for video pages
- Transcript text exposed in page HTML or markdown
- Show notes with transcript-like conversational blocks
- Cleaned descriptive page text only as fallback
Workflow
-
Classify the source:
video_pageyoutube_channelpodcast_pagepodcast_landing- generic
web
-
For
video_page:- fetch page HTML
- extract player response metadata
- locate caption tracks
- prefer English human captions, then English auto-captions
- parse
json3or XML transcript payloads
-
For podcast or transcript-like pages:
- search for headings like
Transcript,Episode transcript,Show transcript,Show notes - capture timestamped lines
- strip timestamps only after preserving ordering
- search for headings like
-
Normalize:
- remove UI chrome
- remove timestamps when compiling plain text
- collapse whitespace
- preserve speaker turns when available
Keep
- opening thesis
- repeated mental models
- self-descriptions
- practical advice
- tradeoffs and caveats
- examples and stories that reveal operating style
Remove
- player controls
- likes/views/share chrome
- subscription prompts
- embed/widget boilerplate
- unrelated recommendations
Weighting Rules
- transcript text should outrank generic page text
- direct episode transcripts should outrank channel pages
- self-authored or self-spoken material should outrank testimonials
- short fragments like
Watch full videoare not transcripts
Validation
A transcript pass is acceptable when:
- it contains coherent clauses, not just labels
- it materially improves over page summary text
- it is tied to a specific episode or identifiable source
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.
- 7d ago First seen · 92 lines · 45 tokens per session scan A bf7dca84f94d
transcript-ingestion is a skill published in the GitHub repository LuuOW/meridian-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 599 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 2026-09-03.
Other skills, from other repositories
transcript-cleanup
Cleans and formats a raw auto-generated podcast transcript for publication on a website or show page — removing filler words and transcription errors, adding speaker labels, formatting for readability, and preserving the authentic voice of host and guests.
data-cleaning-brief
Writes clear, step-by-step instructions for cleaning a messy or inconsistent dataset — specifying exactly what needs to be standardised, corrected, or removed to make the data ready for analysis and publication.
rag-prep
A document-preparation skill that cleans and structures source files for retrieval systems, which find relevant passages from a document collection.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.