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/jared833/claude-code-hooks/coloring-booknpx skills add jared833/claude-code-hooks --skill coloring-bookgit clone --depth 1 https://github.com/jared833/claude-code-hooksWrote 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/jared833/claude-code-hooks/coloring-book)<a href="https://agentmods.dev/skills/jared833/claude-code-hooks/coloring-book"><img src="https://agentmods.dev/badge/skills/jared833/claude-code-hooks/coloring-book.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.02167 |
| Opus 5 | $0.00042 | $0.01084 |
| Sonnet 5 | $0.00017 | $0.00433 |
| Haiku 4.5 | $0.00008 | $0.00217 |
Grade A, and why
coloring-book 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 3d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coloring book production
Built and verified 2026-08-09 on the faith/scripture coloring book (Canva design
<CANVA-DESIGN-ID>). The market benchmark that justified this niche: Coco Wyo's
"Spooky Cutie" coloring book, BSR #88, 7,649 ratings, plus a faith-specific
indie comparable at BSR #32,108, both confirmed live on Amazon before this
skill was written. Re-verify comparables before starting a new theme; don't
trust old numbers.
Prerequisites
- Canva Pro must be active on the account. Confirmed live 2026-08-09 by exporting a design containing a Pro-only element and checking the actual output file (not the editor thumbnail, which renders clean regardless of license): no watermark, full resolution. If a fresh check shows a watermark, Pro lapsed; stop and tell Jared before building more pages.
- The Canva MCP connector (
claude.ai Canva) should be connected, useful for verification (export-design,get-export-formats) and for reusing an asset already placed once (edit-designwithinsert_fillbymediaId), but it cannot search Canva's stock Elements library. That discovery step is browser-only; see below.
Page geometry (KDP paperback, square trim)
Every page is a custom-size Canva design at 8.625in by 8.75in, that's the
8.5in by 8.5in trim size (matching the Coco Wyo benchmark) plus KDP's bleed
spec: add 0.125in to width, 0.25in to height, applied via Canva's Custom Size
dialog with units switched to in. Set this once per design; every added
page inherits it.
KDP's custom trim range is width 4 to 8.5 inches, height 6 to 11.69 inches,
confirmed directly against kdp.amazon.com/en_US/help/topic/G201834180, not
from memory. Re-check if trim size changes.
Not yet built into the layout: a gutter margin (extra inside margin near the spine, which grows with page count) and front matter (title/copyright page before content). Centered art has held up fine at this page count but this is a known gap; fix in the finishing pass before final export, not page by page.
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.
- 3d ago First seen · 154 lines · 84 tokens per session scan A fb6ddd03409d
coloring-book is a skill published in the GitHub repository jared833/claude-code-hooks (2 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 2,167 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
dsh-translate-docs
Manually run the extended DeepSeek Harness bilingual-document workflow, including generated briefings, delegated prose translation, whole-document translation, and scoped pairing verification.
translate-doc-zh
Translate an English document under docs/en/ into the matching Chinese document under docs/zh/.
pdf_translator
Extract text from PDF files, translate it to a target language, and save the result as a Markdown file. Use this skill when the user wants to translate a PDF document or asks to "convert PDF to Chinese".
translate-book
Translate books (PDF/DOCX/EPUB) into any language using parallel sub-agents. Converts input -> Markdown chunks -> translated chunks -> HTML/DOCX/EPUB/PDF.
docs-en-improvement
Improve English documentation under packages/document/docs/en by rewriting unnatural translated sentences into clear, professional English while preserving meaning. Use when editing or polishing English docs in the Rsdoctor project.
procesar-mis-estados-de-cuenta
Proceso un lote de estados de cuenta bancarios y de tarjeta de crédito en PDF o CSV de principio a fin: extraigo cada transacción (subagentes Haiku en paralelo), normalizo los nombres de las contrapartes, categorizo contra tu plan de cuentas bloqueado (subagentes Sonnet en paralelo), detecto transferencias entre…