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 skills/vre/flow-state/litenpx skills add vre/flow-state --skill litegit clone --depth 1 https://github.com/vre/flow-stateWhat 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 | $0.00035 | $0.00886 |
| Opus 5 | $0.00017 | $0.00443 |
| Sonnet 5 | $0.00007 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
youtube-to-markdown scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube to Markdown (Lite Variant)
Optimized variant: No polish steps (4, 7, 8) + combined workflows (5+6, 10a+10b). Result: 2 subagents for minimum cost.
Execute all steps sequentially without asking for user approval.
Step 0: Check extracted before
python3 ./check_existing.py "<YOUTUBE_URL>" "<output_directory>"
If returns exists: true: Skip to Step 10 (comments).
Step 1: Extract data
python3 extract_data.py "<YOUTUBE_URL>" "<output_directory>"
Step 2: Extract transcript
If video language is en, proceed directly. If non-English, ask user which language.
python3 extract_transcript.py "<YOUTUBE_URL>" "<output_directory>" "<LANG_CODE>"
Fallback (only if transcript unavailable)
python3 extract_transcript_whisper.py "<YOUTUBE_URL>" "<output_directory>"
Step 3: Deduplicate transcript
python3 ./deduplicate_vtt.py "<output_directory>/${BASE_NAME}_transcript.vtt" "<output_directory>/${BASE_NAME}_transcript_dedup.md" "<output_directory>/${BASE_NAME}_transcript_no_timestamps.txt"
Copy dedup as final transcript (no polish steps):
cp "<output_directory>/${BASE_NAME}_transcript_dedup.md" "<output_directory>/${BASE_NAME}_transcript.md"
Step 5: Summarize transcript (combined summarize + tighten)
task_tool:
- subagent_type: "general-purpose"
- model: "sonnet"
- prompt:
INPUT: <output_directory>/${BASE_NAME}_transcript_no_timestamps.txt
OUTPUT: <output_directory>/${BASE_NAME}_summary_tight.md
FORMATS: ./summary_formats.md
1. Classify content type:
- TIPS: gear reviews, rankings, practical advice
- INTERVIEW: podcasts, conversations, Q&A
- EDUCATIONAL: concept explanations, analysis
- TUTORIAL: step-by-step instructions
2. Read FORMATS and create summary using format for detected type.
3. Self-review: Cut fluff, enforce <10% of transcript bytes, prefer lists over prose.
4. Save final tightened summary to OUTPUT.
Rules:
- Skip ads, sponsors, self-promotion
- Preserve original language
ACTION REQUIRED: Use Write tool NOW to save to OUTPUT file.
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 · 133 lines · 35 tokens per session scan A e645d0fdad52
youtube-to-markdown is a skill published in the GitHub repository vre/flow-state (12 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 886 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 2026-08-30.
Other skills, from other repositories
myslide
Create professional AWS-themed PowerPoint presentations with dark gradient backgrounds, AWS brand colors, and rich visual elements (SVG diagrams, architecture diagrams, icons). Uses the official AWS reInvent 2023 template design system. Supports creating from scratch, editing specific slides conversationally, and…
account-status
Generate a account status report by taking an account name, analyze spend trends and AWS account mappings, create an HTML report, render chart image for email compatibility, ask recipient email after report completion, and send immediately without reconfirmation. All analysis and email narrative must be in Korean.
memory-manager
Comprehensive memory management for agents. Use when working with memory files (MEMORY.md, memory/.md), searching historical context, managing daily logs, or organizing long-term knowledge. Includes memorysearch and memoryget tools,file management utilities, and best practices for curating agent memory.
source-management
Manages connected MCP sources for enterprise search. Detects available sources, guides users to connect new ones, handles source priority ordering, and manages rate limiting awareness.
retrieve
Search a knowledge base using Amazon Bedrock RAG (Retrieval-Augmented Generation). Use when users want to find information from uploaded documents, ask questions about stored knowledge, or retrieve relevant content from the knowledge base. Returns matched content with source references and URLs.
travel-planner
旅行/行程规划需求时使用:规划去某地旅行、X天X城、带老人孩子、自驾、假期安排等。产出逐日行程表、预算估算(经济/舒适/奢华三档)、交通住宿建议、景点美食清单。必须先问预算,预算未确认只输出问题清单;事实数据带来源和查询日期。.