What is jina-capture?

A command for saving a web page as clean Markdown in a wiki's raw folder. Markdown is plain text formatted for readable notes, and the command uses the Jina Reader service to fetch the page.

Use it when you provide a URL and want to capture an article, import several links, or save reading material to a second-brain wiki.

It gives you a consistent local copy of an article or other web page for later reference, without keeping the original page's cluttered layout.

How slowww-ai/second-brain configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to slowww-ai/second-brain. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/slowww-ai/second-brain/main/.claude/skills/jina-capture/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/slowww-ai/second-brain

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/slowww-ai/second-brain/jina-capture/github.svg)](https://agentmods.dev/skills/slowww-ai/second-brain/jina-capture)

Your own site

<a href="https://agentmods.dev/skills/slowww-ai/second-brain/jina-capture"><img src="https://agentmods.dev/badge/skills/slowww-ai/second-brain/jina-capture/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/slowww-ai/second-brain/jina-capture"><img src="https://agentmods.dev/badge/skills/slowww-ai/second-brain/jina-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,207 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00110	$0.01207
Opus 5.5	$0.00044	$0.00483
Sonnet 5.5	$0.00022	$0.00241
Haiku 4.5	$0.00011	$0.00121

Measured 1mo ago against content hash 88ce1b04040a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

jina-capture 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 1mo 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 -sL "https://r.jina.ai/<url>" -o /tmp/jina.md

.claude/skills/jina-capture/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capture (Jina + YouTube)

Turn any URL into a stamped markdown file in wiki/raw/. Two backends, one contract:

Web pages → Jina Reader (https://r.jina.ai/<url>) returns the page as clean markdown.
YouTube videos → scripts/yt_capture.py saves the transcript (manual captions preferred, auto-generated fallback; language priority ko,en).

When to use

User provides a URL and wants it captured into the second brain.
User says "save this", "capture this", "add to raw", "read this later", etc., alongside a link.
User gives a YouTube link and wants the transcript saved.
Bulk import of a list of URLs (mixed article/YouTube lists are fine — route each one).

Steps

Confirm target folder. Default is wiki/raw/ in the current project (the second brain repo). If the user is not in that repo, ask where to save.
Route by URL type. If the URL matches youtube.com/watch, youtu.be/, youtube.com/shorts/, youtube.com/embed/, or youtube.com/live/, take the YouTube branch (step 3). Everything else takes the Jina branch (step 4).
YouTube branch. Run the capture script — it handles everything (oEmbed title/channel, transcript fetch, paragraphing with [mm:ss] markers, frontmatter, slug collisions):
```
.venv/bin/python scripts/yt_capture.py <url> [<url> ...]
```
- Multiple YouTube URLs can be passed in one call; it prints one saved: line per file.
- To change transcript language priority: --langs ko,en (that's the default).
- If it errors with "transcripts are disabled" or "no transcript found", tell the user; offer yt-dlp or Whisper transcription as the fallback only if they want to pursue it.
- Skip to step 6 (report back).
Jina branch — fetch the markdown. For each URL:
- Construct https://r.jina.ai/<url> (do not URL-encode the target — Jina expects the raw URL appended).
- Use the WebFetch tool to retrieve it. Ask for the full markdown body.
- If WebFetch summarizes instead of returning raw content, fall back to:
```
curl -sL "https://r.jina.ai/<url>" -o /tmp/jina.md
```
  and read /tmp/jina.md.

Read the full file on GitHub · 84 lines

Changes

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.

1mo ago Changed · +19 lines · +32 tokens per session 88ce1b04040a
2mo ago First seen · 65 lines · 78 tokens per session scan A 9fb61514e13b

Subscribe to this mod's changes

jina-capture is a skill published in the GitHub repository slowww-ai/second-brain (10 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 1,207 once invoked, about $0.0004 per session on Opus 5.5. 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.

Research Writing and docs

jina-capture next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
jina-captureslowww-ai/second-brain	Skill	10	1mo ago	MIT	A	110	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

second-brain: Skill for Claude Code