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 chanshawoh/imageforge-mcp --skill use-imageforge-mcpgit clone --depth 1 https://github.com/chanshawoh/imageforge-mcpWrote 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/chanshawoh/imageforge-mcp/use-imageforge-mcp)<a href="https://agentmods.dev/skills/chanshawoh/imageforge-mcp/use-imageforge-mcp"><img src="https://agentmods.dev/badge/skills/chanshawoh/imageforge-mcp/use-imageforge-mcp/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/chanshawoh/imageforge-mcp/use-imageforge-mcp"><img src="https://agentmods.dev/badge/skills/chanshawoh/imageforge-mcp/use-imageforge-mcp.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 | $0.00079 | $0.02676 |
| Opus 5 | $0.00039 | $0.01338 |
| Sonnet 5 | $0.00016 | $0.00535 |
| Haiku 4.5 | $0.00008 | $0.00268 |
Grade A, and why
use-imageforge-mcp 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 4d 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use ImageForge MCP
Use the configured ImageForge MCP server and its list_image_providers, generate_image, or edit_image tool; the client-side server name may vary by installation. Do not substitute another image-generation tool when ImageForge is available for the requested capability.
Choose the provider and tool
| User intent | Tool | Provider | Important constraint |
|---|---|---|---|
| Text-to-image with OpenAI | generate_image |
openai |
Model must be gpt-image-2 |
| Text-to-image with Zhipu | generate_image |
zhipu |
Text prompt only |
| Text-to-image with MiniMax | generate_image |
minimax |
image-01 or image-01-live; JPEG output |
| Generate from reference images | generate_image with reference_images |
openai or minimax |
OpenAI: 1–16; MiniMax: one PNG/JPEG subject reference under 10 MB |
| Edit existing images | edit_image with input_images |
OpenAI only | Zhipu and MiniMax editing are not implemented |
| Request Zhipu watermark behavior | generate_image with watermark_enabled |
zhipu |
false may require account authorization |
| Request MiniMax watermark behavior | generate_image with watermark_enabled |
minimax |
Maps to aigc_watermark |
Additional provider IDs are google, xai, stability, ideogram, recraft, tencent, baidu, playground, bfl, luma, krea, runway, leonardo, bria, freepik, alibaba, volcengine, kling, and hidream. Call list_image_providers before using one of them; its result is authoritative for model names, reference modes, limits, credential environment variables, and whether the adapter has live verification.
Set provider explicitly whenever the capability or model depends on the provider. If omitted, the server uses IMAGEFORGE_PROVIDER, then defaults to OpenAI.
Never silently:
- drop
reference_imagesfrom a Zhipu request; - switch a user-requested Zhipu call to OpenAI;
- claim that Zhipu supports editing or reference-image generation;
- claim that MiniMax supports editing, multiple references, WebP references, or non-JPEG output;
- claim that
watermark_enabled: falselocally removes a watermark. - treat official-documentation contract tests as proof that a live credential or paid account works.
What ships with it
1 file 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.
- 4d ago Changed · +3 lines · -5 tokens per session ae9a3238f97c
- 9d ago First seen · 217 lines · 84 tokens per session scan A 055fdbe4c10c
use-imageforge-mcp is a skill published in the GitHub repository chanshawoh/imageforge-mcp (2 stars, last pushed 9d ago), licensed MIT. It adds 79 tokens to every session and 2,676 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
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.