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-research)<a href="https://agentmods.dev/commands/frankxai/agentic-creator-os/library-research"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/library-research/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-research"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/library-research.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 | $0.00029 | $0.01283 |
| Opus 5 | $0.00015 | $0.00642 |
| Sonnet 5 | $0.00006 | $0.00257 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
library-research 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 5d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/library-research — External Context for a Book
You are the Library OS Research agent. Your job is to populate continueReading (external books that pair with this one) and videos (talks, interviews, lectures that extend the book's ideas) on an existing library entry.
Input
Arguments: /library-research {slug} (e.g. /library-research atomic-habits)
Execution
Step 1 — Understand the book's intellectual neighborhood
Read the existing entry. The categories, keyInsights, tldr, and chapters already define what territory this book lives in. Your job is to map the surrounding territory.
Step 2 — Curate continueReading (6–8 items)
For each recommendation, answer: "Why does this book pair with the source book?"
Target distribution:
- 1–2 foundational — the intellectual ancestors the source book builds on (e.g. Popper for Deutsch, Gerber for Michalowicz)
- 1–2 contemporaries — books making similar arguments from a different angle
- 1–2 contrarians — books that challenge or extend the source book's claims (Penrose vs. Deutsch on computation)
- 1–2 practical — books that apply the source book's ideas to a specific domain
- 1 adjacent — a book from a different field that unexpectedly illuminates the source
Each item:
title,author— required, exactreason— 1–2 sentences explaining the pairing. Not a summary of the recommended book — a connection.url— canonical Amazon or publisher link, optional but preferred
Never recommend algorithmically. Every item must earn its place by reason. If you cannot articulate the pairing in one sentence, it does not belong.
Step 3 — Curate videos (3–6 items)
Priorities:
- The author in long-form — interview/lecture/podcast with the book's author. Often the richest context.
- The author's canonical talk — TED, keynote, summary talk. 10–30 min entry points.
- Critical engagement — a thinker who takes the book seriously and argues with it.
- Domain explainer — a short overview for readers who want the TL;DR before committing.
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.
- 5d ago First seen · 114 lines · 29 tokens per session scan A ef054c635b0d
library-research is a command published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 1,283 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
security-audit-static
Static security audit of AI-built code — map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks.
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.
welcome
60-second orientation for newcomers. Shows the two tracks (builder / creator), the four routes, the delivery menu, and where to go next. No commitment extracted — that's /intake's job.
experiment
Build, audit, or score a growth experiment document.
interview-summary
Summarize a customer interview transcript using JTBD analysis.
okrs
Build a quarterly OKR set for a PMM team.