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.
git clone --depth 1 https://github.com/frankxai/agentic-creator-osWrote 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/commands/frankxai/agentic-creator-os/library-deepen)<a href="https://agentmods.dev/commands/frankxai/agentic-creator-os/library-deepen"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/library-deepen/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/commands/frankxai/agentic-creator-os/library-deepen"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/library-deepen.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 | $0.00027 | $0.00948 |
| Opus 5.5 | $0.00011 | $0.00379 |
| Sonnet 5.5 | $0.00005 | $0.00190 |
| Haiku 4.5 | $0.00003 | $0.00095 |
Grade A, and why
library-deepen 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 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.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/library-deepen — Deep-Dive an Existing Book
You are the Library OS Deep-Dive agent. Your job is to take an existing library entry and upgrade it into a single-page knowledge hub by populating quotes, chapters, and triggering the research agent for continueReading + videos.
Input
Arguments: /library-deepen {slug} (e.g. /library-deepen atomic-habits)
Optionally: --source=path/to/book.pdf or --source=path/to/notes.md to base extraction on the actual text.
Execution
Step 1 — Load the entry
Read data/book-reviews.ts, find the entry by slug. If the book does not exist yet, run /library-add first.
Step 2 — Curate quotes
Target: 10–20 quotes that are:
- Memorable — short enough to quote (ideally under 30 words)
- Load-bearing — carry a key idea, not just rhetoric
- Distributed — spread across the book, not clustered in one chapter
- Attributable — each ends with a
chapterreference in the data
Delegate to the book-distiller subagent with the book title + author + source (if provided) + target count. The subagent returns BookQuote[] in the exact shape of the type.
Each quote MUST include:
text— the quote verbatim (or the best English translation)chapter—"Chapter 3 — Problem-Solving"format (include both number and title)context(optional) — one sentence framing why this quote matters
Step 3 — Distill chapters
Target: every chapter of the book, no exceptions. Each chapter gets:
number— 1-indexedtitle— exact chapter titlekeyIdea— one sentence, the chapter's thesissummary— 2–4 sentences, what the chapter argues
Delegate to book-distiller with mode: 'chapters'. Returns BookChapterSummary[].
Step 4 — Offer research handoff
Print:
Quotes added: N
Chapters added: N
Run /library-research {slug} to populate continueReading + videos.
Step 5 — Type-check + preview
npx tsc --noEmit data/book-reviews.ts
Optionally, fetch the rendered page in dev to sanity-check: the TOC should now list Quotes + Chapter-by-Chapter sections.
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 First seen · 94 lines · 27 tokens per session scan A 20894def1b26
library-deepen is a command published in the GitHub repository frankxai/agentic-creator-os (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 948 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other commands, from other repositories
document-app
Reverse-engineer an AI-built codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply. check mode writes nothing and reports where the existing docs and the code disagree.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.
csv-to-numbers
Convert a CSV into a formatted Numbers workbook.
recap
Get a summary of everything you learned this session — concepts, quizzes, and progress.
summarize-pdf
A command that reads a technical book in PDF format chapter by chapter and organises the material into Obsidian notes. Obsidian is a note-taking app that stores linked notes as files.
set-okrs
Structure OKRs — define objectives, write measurable key results, align to strategy, stress-test for quality, and cascade across teams.