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 jtprogru/bear-skills --skill book-highlights-processorgit clone --depth 1 https://github.com/jtprogru/bear-skillsWrote 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/jtprogru/bear-skills/book-highlights-processor)<a href="https://agentmods.dev/skills/jtprogru/bear-skills/book-highlights-processor"><img src="https://agentmods.dev/badge/skills/jtprogru/bear-skills/book-highlights-processor/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/jtprogru/bear-skills/book-highlights-processor"><img src="https://agentmods.dev/badge/skills/jtprogru/bear-skills/book-highlights-processor.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 | $0.00078 | $0.00963 |
| Opus 5 | $0.00039 | $0.00481 |
| Sonnet 5 | $0.00016 | $0.00193 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade A, and why
book-highlights-processor 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 8d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Book Highlights Processor
Transform exported book highlight files into enriched Obsidian callouts with AI-generated titles and highlighted key phrases.
Input format
The markdown file from iBooks or Zotero looks like this:
---
book: Book Title
author: Author Name
language: ru
tags:
- ibook/imported
- literature
---
## 📔 Книга: Book Title
**Автор**:: Author Name
...
---
# 🔍 How I Discovered IT
- 📚
- 🎯Quote text here, possibly several sentences or paragraphs
- ✍️Reader's own note or commentary (optional)
- 🎯Another quote
- ✍️Another note
What to produce
For each 🎯 quote, output an Obsidian callout:
> [!quote] Generated Title
> Quote text with ==key phrase== and ==another key phrase== highlighted.
>
> ✍️ Reader's note text
If the quote has no ✍️ note, omit the last line.
Never add commentary of your own — no summary line before the quote, no takeaway after it. The callout carries the source's words, the reader's note and nothing else; anything explaining the quote back to the reader is the filler .agents/rules/note-density.md forbids.
How to generate the title
The title goes into the callout header and will likely become the filename of a future Obsidian atomic note. Naming style (claim-based, 4–8 words, language rules) — see .agents/rules/file-naming.md.
Draw on the ✍️ reader note as a signal of what the reader found important — that's the insight to encode in the title, not just a paraphrase of the raw quote.
Examples from SRE context:
- "Мониторинг min/max ловит сбои, которые среднее скрывает"
- "Fallback должен существовать даже в виде тетриса"
- "Graceful Degradation требует нескольких уровней готовности"
- "Ретраи без backoff превращают деградацию в катастрофу"
How to add highlights
Add ==highlight== to 2–4 phrases per quote. Choose phrases that:
- Carry the core claim or mechanism
- Help a reader scanning the quote instantly grasp the main point
- Are short (3–8 words each)
What ships with it
2 files 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.
- 8d ago First seen · 121 lines · 78 tokens per session scan A 92b8c3f5e1d1
book-highlights-processor is a skill published in the GitHub repository jtprogru/bear-skills (1 stars, last pushed 21d ago), licensed MIT. It adds 78 tokens to every session and 963 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
using-dinf
WHAT: the D∞ notation — the ⟨parts | Ω⟩ shape every durable teaching, framework, plan, and joke has — plus the three operators over it (FACTOR, ADJOIN, CHRISTEN) and the dinf CLI that makes the missing-closure defect machine-catchable. WHEN: when stuck; when a plan feels like unjoined parts; when two frames are…
enablement-course
Assemble an internal AI enablement course for a company's own employees, sized to where they actually are rather than where a vendor deck assumes they are. Produces the session plan, per-session content and exercises, a facilitator guide for a non-expert, and a way to tell whether it worked. Builds on the tech stack…
meta-tags-optimizer
Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…
paid-ads-linkedin
Audit, diagnose, plan, and safely operate connected LinkedIn Ads accounts through the NotFair MCP, with an export-based fallback. Use for LinkedIn advertising, sponsored content, lead-generation forms, job-title or company targeting, campaign groups, creatives, conversions, lead quality, budgets, bids, or approved…
paid-ads-guide
Explain NotFair's paid-ads skills, installation, platform boundaries, account connections, and current product capabilities. Use for questions about how NotFair works, what it supports, how to install or connect it, plans or limits, or paid-media troubleshooting that is not an account-performance request.
case-interview-practice
Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.