Raven is an open-source agent harness for running long-term AI work with terminal execution, tracing, memory, skills, evaluation, and reusable workflows. People use the current release to operate and improve persistent AI workflows, while its described future direction is a multi-agent system that combines specialized harnesses.
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 EverMind-AI/Raven --skill image-gengit clone --depth 1 https://github.com/EverMind-AI/RavenWrote 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/evermind-ai/raven/image-gen)<a href="https://agentmods.dev/skills/evermind-ai/raven/image-gen"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/image-gen.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.01329 |
| Opus 5 | $0.00024 | $0.00665 |
| Sonnet 5 | $0.00010 | $0.00266 |
| Haiku 4.5 | $0.00005 | $0.00133 |
Grade A, and why
image-gen scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import os, base64, json, urllib.request How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
image-gen — Nano Banana via OpenRouter
Generates one or more images from a text prompt (and optionally one or more input images) by calling Google's Nano Banana family on OpenRouter:
google/gemini-2.5-flash-image— original (Nano Banana)google/gemini-3.1-flash-image-preview— latest (Nano Banana 2)
OpenRouter speaks the OpenAI-compatible chat-completions API for these models, with two extras:
- The request must include
"modalities": ["image", "text"]so the server knows to return image bytes, not just a description. - The response carries images in a top-level
message.imagesarray (NOT incontent— that field still holds optional commentary text).
Quick recipe
import os, base64, json, urllib.request
KEY = os.environ["OPENROUTER_API_KEY"]
MODEL = "google/gemini-2.5-flash-image" # or 3.1 for "Nano Banana 2"
def generate_image(prompt: str, out_path: str = "out.png") -> str:
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({
"model": MODEL,
"messages": [{"role": "user", "content": prompt}],
"modalities": ["image", "text"],
}).encode(),
headers={
"Authorization": f"Bearer {KEY}",
"Content-Type": "application/json",
},
method="POST",
)
with urllib.request.urlopen(req, timeout=120) as resp:
data = json.loads(resp.read())
msg = data["choices"][0]["message"]
# ``message.images[i].image_url.url`` is a data URI:
# "data:image/png;base64,<base64-bytes>"
url = msg["images"][0]["image_url"]["url"]
b64 = url.split(",", 1)[1]
with open(out_path, "wb") as f:
f.write(base64.b64decode(b64))
text_note = msg.get("content") or ""
return f"Wrote {out_path} ({len(b64)//1024} KB). Model said: {text_note[:200]!r}"
Request shape (full)
{
"model": "google/gemini-2.5-flash-image",
"messages": [
{"role": "user", "content": "A red circle on white background"}
],
"modalities": ["image", "text"]
}
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.
- 8d ago First seen · 152 lines · 48 tokens per session scan A 29cdb27e062d
image-gen is a skill published in the GitHub repository EverMind-AI/Raven (3,768 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 1,329 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
p5js
Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
audiocraft-audio-generation
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
concept-diagrams
Generate flat, minimal educational SVG visuals as HTML.
hyperframes
Render MP4/WebM videos from HTML compositions.
touchdesigner-mcp
Control TouchDesigner via twozero MCP.
baoyu-comic
A creator for educational comics, including biographies and tutorials, that turns supplied content or topics into illustrated comic pages.