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 fortunto2/solo-factory --skill you2idea-extractgit clone --depth 1 https://github.com/fortunto2/solo-factoryWrote 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/fortunto2/solo-factory/you2idea-extract)<a href="https://agentmods.dev/skills/fortunto2/solo-factory/you2idea-extract"><img src="https://agentmods.dev/badge/skills/fortunto2/solo-factory/you2idea-extract/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/fortunto2/solo-factory/you2idea-extract"><img src="https://agentmods.dev/badge/skills/fortunto2/solo-factory/you2idea-extract.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 | $0.00068 | $0.01399 |
| Opus 5 | $0.00034 | $0.00700 |
| Sonnet 5 | $0.00014 | $0.00280 |
| Haiku 4.5 | $0.00007 | $0.00140 |
Grade A, and why
solo-you2idea-extract 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 12d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/you2idea-extract
Extract startup ideas from YouTube videos. Two operating modes depending on available tools.
Mode Detection
Check which tools are available:
- With solograph MCP: use
source_search,source_list,source_tags,source_relatedfor indexed corpus - Without MCP (standalone): use yt-dlp + Read for transcript analysis
MCP Tools (if available)
source_search(query, source="youtube")— semantic search over indexed videossource_list()— check indexed video countssource_tags()— auto-detected topics with confidence scoressource_related(video_url)— find related videos by shared tagskb_search(query)— cross-reference with knowledge baseweb_search(query)— discover new videos to indexweb_extract(url, size, page)— read a linked article as clean markdown
Steps
Mode 1: Index + Analyze (with solograph MCP)
-
Parse input from
$ARGUMENTS:- URL (
https://youtube.com/watch?v=...) → single video index - Channel name (
GregIsenberg) → channel batch index - Query text → search existing corpus (skip to step 4)
- If empty, ask: "Video URL, channel name, or search query?"
- URL (
-
Index video(s) via solograph:
# Install if needed pip install solograph # or: uvx solograph # Single video solograph-cli index-youtube -u "$URL" # Channel batch (needs web search for discovery) solograph-cli index-youtube -c "$CHANNEL" -n 5 -
Verify indexing —
source_list()to confirm new video count.source_tags()for topic distribution. -
Search corpus —
source_search(query="startup ideas", source="youtube"). -
Cross-reference —
kb_search(query)for related existing opportunities (if knowledge base available). -
Extract insights — for each relevant video chunk:
- Identify the startup idea mentioned
- Note timestamp and speaker context
- Rate idea potential (specificity, market evidence, feasibility)
- Flag ideas that match trends or validated patterns
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 134 lines · 68 tokens per session scan A bf9022a38322
solo-you2idea-extract is a skill published in the GitHub repository fortunto2/solo-factory (18 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 1,399 once invoked, about $0.0003 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
harness
Route Harness Starter Kit workflows. Use when the user invokes /harness with adopt, doctor, update, refresh, review, or review sub-agent, or asks to apply, diagnose, maintain, or review repository harness guidance.
product-diagnosis
Six-question diagnostic framework for G0 pre-check — validate product direction before development starts.
review
L1 internal review with auto-detection, design comparison, and Gate escalation path.
dev-plan
Generate a development plan with task breakdown and section 10 tracking tables.
knowledge-feedback
Scan child projects for pitfalls and propose company standard updates.
sop-review
A structured code-review procedure for checking a task against project rules and acceptance criteria. It loads the task, relevant standards, and the Git changes before reviewing every required checkpoint.