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/jaansokk/cursor_tools/summarizernpx skills add jaansokk/cursor_tools --skill summarizergit clone --depth 1 https://github.com/jaansokk/cursor_toolsWhat 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 | $0.00152 | $0.01280 |
| Opus 5 | $0.00076 | $0.00640 |
| Sonnet 5 | $0.00030 | $0.00256 |
| Haiku 4.5 | $0.00015 | $0.00128 |
Grade A, and why
summarizer scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://www.youtube.com/oembed?url=VIDEO_URL&format=json" How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summarizer — YouTube / Podcast → NotePlan
Takes a YouTube video URL, fetches the transcript, writes a practical summary, and saves it as a note in NotePlan under the right channel/creator subfolder.
Workflow
1. Get video metadata
Fetch the video title and channel name using the YouTube oEmbed API:
curl -s "https://www.youtube.com/oembed?url=VIDEO_URL&format=json"
This returns JSON with title and author_name. Extract both — you need them for the note heading and folder name.
If oEmbed fails (private video, age-restricted), fall back to asking the user for the title and channel.
2. Fetch the transcript
Use the bundled yt-transcript script:
python ~/.claude/skills/yt-transcript/scripts/yt_transcript.py "VIDEO_URL"
For Estonian videos, add et as the second argument.
3. Write the summary
Read the full transcript and write a summary following these rules:
Length: Up to 350 words. If the video contains specific scripts, frameworks, step-by-step processes, or concrete examples that lose their value when compressed, go longer — practical detail beats arbitrary brevity.
What to include:
- Core insight — the central thesis or main argument in 1-3 sentences
- Core content, practical tips and frameworks — actionable advice, systems, scripts, checklists. This is the most important part. Preserve specificity — if the speaker says "ask this exact question" or "use this technique" include it. Format this as topic (### heading) and bullets.
- Key mistakes / anti-patterns — what NOT to do, if covered
- Key takeaway — a distilled closing thought
What to skip:
- Sponsor segments, self-promotion, channel plugs
- Repetitive examples that make the same point
- Vague motivational filler ("you've got this!", "believe in yourself")
- Biographical context about the speaker unless it's directly relevant to credibility
Tone: Match the user's existing notes — structured, scannable, practical. Use headers, bullets, bold for key terms. Write like you're capturing a playbook, not summarizing an article.
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 · 121 lines · 152 tokens per session scan A 51564d504f7e
summarizer is a skill published in the GitHub repository jaansokk/cursor_tools (1 stars, last pushed 5mo ago), licensed MIT. It adds 152 tokens to every session and 1,280 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
continuous-discovery
Guide teams through building sustainable customer interview habits and discovery practices. Use when setting up weekly customer interviews, preparing interview guides, coaching story-based interviewing technique, synthesizing user research findings, planning assumption tests, or helping teams that say they don't have…
prd-writer
Guide users through writing Product Requirements Documents (PRDs) and decomposing them into executable technical tasks. Use when creating a PRD, product spec, product one-pager, feature brief, PRP, or when breaking requirements into tasks with estimates, sprint planning, or technical decomposition.
product-led-growth-playbook
Evaluate growth strategy, growth team structure, and go-to-market motions using Elena Verna's PLG frameworks. Use when the user asks about product-led growth, PLG, growth team hiring, self-serve vs sales-led motions, product-led sales, PQA/PQL models, growth loops, when to hire a head of growth, earned vs rented…
ab-testing-framework
Design, run, and analyze A/B tests (controlled experiments) using Ronny Kohavi's methodology and Gibson Biddle's DHM trade-off analysis. Use when the user needs to plan an experiment, choose metrics (OEC), evaluate statistical significance, assess sample size requirements, avoid common experimentation pitfalls, or…
dhm-strategy-framework
Evaluate and strengthen product strategy using Gibson Biddle's DHM framework (Delight, Hard-to-copy, Margin-enhancing). Use when the user asks about product strategy, competitive advantage, feature prioritization trade-offs, or wants to stress-test whether a product idea is strategically sound.
ai-evals-builder
Build AI evals using the Husain-Shankar framework (error analysis, open/axial coding, LLM-as-judge). Use when a user needs to create, improve, or debug evals for an AI product — including defining failure modes, building LLM judges, or setting up production monitoring for an LLM application.