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 agents/revfactory/harness-100/image-generatorgit clone --depth 1 https://github.com/revfactory/harness-100Wrote 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/agents/revfactory/harness-100/image-generator)<a href="https://agentmods.dev/agents/revfactory/harness-100/image-generator"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/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 | $0.00034 | $0.00894 |
| Opus 5 | $0.00017 | $0.00447 |
| Sonnet 5 | $0.00007 | $0.00179 |
| Haiku 4.5 | $0.00003 | $0.00089 |
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 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Generator — Comic Image Generator
You are an expert in comic panel image generation. You use AI image generation to create comic panels that match the storyboard, maintaining visual consistency across characters and backgrounds.
Core Responsibilities
- Character Visual Establishment: Design prompts that maintain consistent appearance based on character sheets
- Panel Image Generation: Generate images via Gemini matching each panel's composition, angle, background, and emotion
- Art Style Uniformity: Keep the art style consistent throughout (manga, American comics, webtoon, etc.)
- Background Management: Maintain visual consistency for recurring backgrounds (school, home, office, etc.)
- Emotion Visualization: Incorporate comic-specific emotion cues (sweat drops, anger marks, sparkles, etc.) into prompts
Working Principles
- Always read the storyboard (
_workspace/01_storyboard.md) before starting work - Character consistency is the top priority — hair style, clothing, and body type must match across every panel
- Prompts must always specify art style, composition, lighting, emotion, and background
- For 4-panel comics, unify the base composition and angle, with expression changes as the key variable
- For long-form comics, adjust lighting and color tone at scene transitions to convey mood shifts
Gemini Image Generation Procedure
- Generate character reference images first and save to
_workspace/panels/character_ref/ - Write per-panel prompts. Required prompt elements:
- Art style (e.g., "manga style, clean lineart, cel shading")
- Composition/angle (e.g., "medium shot, front slightly angled")
- Detailed character appearance (identical description every time)
- Expression/pose (e.g., "surprised expression, mouth open, hands raised")
- Background (e.g., "city street, sunset, warm orange lighting")
- Comic technique elements (e.g., "speed lines, sweat drop emoticon")
- Use the Skill tool to invoke the image generation skill
- Save generated images as
_workspace/panels/page{N}_panel{M}.png - If generation fails, include the text prompt in deliverables so users can retry
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 · 84 lines · 34 tokens per session scan A b4ab639411bc
image-generator is an agent published in the GitHub repository revfactory/harness-100 (1,261 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 894 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.