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 taivop/marketplace --skill coloring-bookgit clone --depth 1 https://github.com/taivop/marketplaceWrote 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/taivop/marketplace/coloring-book)<a href="https://agentmods.dev/skills/taivop/marketplace/coloring-book"><img src="https://agentmods.dev/badge/skills/taivop/marketplace/coloring-book/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/taivop/marketplace/coloring-book"><img src="https://agentmods.dev/badge/skills/taivop/marketplace/coloring-book.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 | $0.00057 | $0.01071 |
| Opus 5 | $0.00028 | $0.00535 |
| Sonnet 5 | $0.00011 | $0.00214 |
| Haiku 4.5 | $0.00006 | $0.00107 |
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 11d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coloring Book Generator
pipeline.py and spec.example.yaml live in this skill's directory (treat it as
read-only — it may be an installed plugin). Everything the pipeline writes —
spec.yaml, .env and the output/ tree — goes in a separate work
directory. Create one for the book (e.g. ~/coloring-book/<title>/), cd into
it, and run the script by its full path from there; the work directory defaults
to the current directory (override with --workdir PATH or $COLORING_BOOK_DIR).
Drive pipeline.py stage by stage. The rule that matters: inspect each stage's
images with Read before running the next stage — a bad character sheet poisons
every page built from it. Fix at the earliest stage.
Setup
- Make a work directory and
cdinto it. Copy the template:cp <skill-dir>/spec.example.yaml spec.yaml, then editspec.yaml. .env(in the work directory) withOPENAI_API_KEY=sk-...(gitignored; ask if missing), or exportOPENAI_API_KEY. Test the key with one cheap generation first —billing_hard_limit_reachedorinsufficient_quotamean the user must add credits, so stop and say so.pip install -r <skill-dir>/requirements.txt.
Workflow
Gather story, characters (or invent), style, audience and page count into
spec.yaml (copied from spec.example.yaml). Run stages in order from the work
directory (python3 <skill-dir>/pipeline.py <stage>), reviewing each before the
next. Paths below (output/...) are relative to the work directory:
| Stage | Command | Review before continuing |
|---|---|---|
| 1. Outline | python3 pipeline.py outline |
Read output/outline.json. Story beats visual-only? Character descriptions specific enough to repeat verbatim? Every wanted landmark present (the model drops some — re-add in the JSON)? Add per-page landmark fields = exact English Wikipedia article titles. |
| 2. Characters | python3 pipeline.py characters |
Read each output/characters/*.png. Same features across poses? Species right? Fix by tightening the description in outline.json, then --only NAME. |
| 3. Landmarks | python3 pipeline.py landmarks |
Read each output/landmarks/*.png. Structure recognizable, proportions right? Aerial/map-style photos anchor badly — drop that page's landmark instead. |
| 4. Pages | python3 pipeline.py pages (slow — run in background) |
Read every page: no text anywhere; correct character count; each character's signature features present; landmark faithful. Redo one page with --page N. |
| 5. PDF | python3 pipeline.py postprocess && python3 pipeline.py pdf |
Deliver output/book.pdf with SendUserFile. |
What ships with it
5 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.
- 11d ago First seen · 74 lines · 57 tokens per session scan A 3c828fa67ab8
coloring-book is a skill published in the GitHub repository taivop/marketplace (17 stars, last pushed 10d ago), licensed MIT. It adds 57 tokens to every session and 1,071 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
wowerpoint
Turn one document into a kawaii NotebookLM slide-deck PDF. Use for "wowerpoint this", "make a deck about ", "turn this report into slides", or any request to render a single document as shareable narrative slides.
pptx-posters
Create research posters using HTML/CSS that can be exported to PDF or PPTX. Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format. For standard research posters, use latex-posters instead. This skill provides modern web-based poster design with responsive layouts and easy visual…
slides
Create and edit presentation slide decks (.pptx) with PptxGenJS, bundled layout helpers, and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding…
pptx
Create and validate Microsoft PowerPoint presentations (.pptx), including structured slide decks, tables, workflows, metadata, and reproducible generation scripts. Use for presentation, slides, PowerPoint, PPT, or PPTX creation and verification tasks.
utility-slideshow-creator
Generates professional presentations from a JSON deck specification using 18 slide types with dark/light variants, content-to-layout decision logic, and calibrated character limits. Ships with a default professional theme.
timecode-audio-edit-workflow
The patch comprehensively addresses all identified issues.