Borrowing it
Nothing to install: this file belongs to lowtidebuild/ebook-writer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lowtidebuild/ebook-writer/main/.claude/skills/image-generator/SKILL.mdgit clone --depth 1 https://github.com/lowtidebuild/ebook-writerWrote 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/lowtidebuild/ebook-writer/image-generator)<a href="https://agentmods.dev/skills/lowtidebuild/ebook-writer/image-generator"><img src="https://agentmods.dev/badge/skills/lowtidebuild/ebook-writer/image-generator.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 5.1 | $0.00000 | $0.01244 |
| Opus 5 | $0.00000 | $0.00622 |
| Sonnet 5 | $0.00000 | $0.00249 |
| Haiku 4.5 | $0.00000 | $0.00124 |
Grade A, and why
image-generator 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 7d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Generator Skill
Purpose
Extract [IMAGE: ...] markers from generated chapter files, generate matching images via a per-entry image provider, and insert the resulting images back into the markdown chapters. Four providers are supported and each entry is routed by image_type:
diagram(default for text-heavy diagrams:architecture,process_flow,comparison_table) — deterministic local SVG renderer. No API key, network, or private backend required.gemini(default for illustrative types:concept_diagram,metaphor) — Google Gemini multimodal image output. Cheap, stable.openai(explicit override only) — paid OpenAI Images API (gpt-image-*). Available when callers want the supported public API.codex(explicit override only) — routes through god-tibo-imagen using local Codex CLI auth (~/.codex/auth.json). Backend is unsupported by OpenAI and may break without warning.
Failed entries remain blocking in final preflight. Insertion uses a neutral caption fallback instead of a visible [이미지 생성 실패] production artifact.
Pipeline
The skill operates as a 4-step script pipeline executed in order:
Step 1: Extract Markers (extract_markers.py)
Scans all .md chapter files for [IMAGE: description] patterns and produces an image_manifest.json listing every marker with its location, description, and a pending status.
.venv/bin/python3 .claude/skills/image-generator/scripts/extract_markers.py output/chapters/ko/ output/images/image_manifest.json
Step 2: Classify & Generate Prompts (generate_prompts.py)
The orchestrator first classifies each marker's image_type (concept_diagram, process_flow, comparison_table, architecture, metaphor) based on the description. Then generate_prompts.py applies type-specific prompt templates from references/prompt_templates/ to generate prompts, assigns each entry a provider, and fills output_path with the provider-specific extension. Set IMAGE_PROVIDER=diagram|codex|gemini|openai to override globally.
What ships with it
11 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.
- references/image_style_guide.md 2.9 KB
- references/prompt_templates/architecture.txt 749 B
- references/prompt_templates/comparison_table.txt 638 B
- references/prompt_templates/concept_diagram.txt 575 B
- references/prompt_templates/generic.txt 348 B
- references/prompt_templates/metaphor.txt 682 B
- references/prompt_templates/process_flow.txt 666 B
- scripts/extract_markers.py 3.4 KB runs code
- scripts/generate_images.py 12 KB runs code
- scripts/generate_prompts.py 5.8 KB runs code
- scripts/insert_images.py 4.5 KB runs code
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.
- 7d ago First seen · 80 lines · 0 tokens per session scan A 909d1bafe45d
image-generator is a skill published in the GitHub repository lowtidebuild/ebook-writer (5 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,244 tokens. 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.