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 nanoodlecom/nanoodle-mcp --skill noodlesgit clone --depth 1 https://github.com/nanoodlecom/nanoodle-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/nanoodlecom/nanoodle-mcp/noodles)<a href="https://agentmods.dev/skills/nanoodlecom/nanoodle-mcp/noodles"><img src="https://agentmods.dev/badge/skills/nanoodlecom/nanoodle-mcp/noodles/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/nanoodlecom/nanoodle-mcp/noodles"><img src="https://agentmods.dev/badge/skills/nanoodlecom/nanoodle-mcp/noodles.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 | $0.00072 | $0.00667 |
| Opus 5 | $0.00036 | $0.00333 |
| Sonnet 5 | $0.00014 | $0.00133 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
noodles 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 10d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What a noodle is
A noodle is a workflow graph built visually in the nanoodle
editor: a feed-forward DAG of AI nodes (LLM, image, video, audio, edit, ...) that
runs on the NanoGPT API with the user's own key. Saved graphs are
noodle-graph.json files. This plugin's MCP server scans one directory of those
files at startup and serves each file as one MCP tool.
Facts that matter when calling these tools
- Every call spends real money from the user's nano-gpt.com balance. Don't
loop or retry aggressively; the final content block of every result reports
the run's cost as
cost: $X.XXXX. Surface that cost to the user. - All inputs are strings. Media-typed inputs (image / audio / video) accept
a local file path or an
https://URL. Local paths are read and sent inline (base64) — there is a ~4 MB cap, checked before any money is spent. - Text outputs come back as text blocks. Media outputs are saved to the
server's output directory and the result block gives the absolute saved path
(e.g.
Image: saved /path/to/poster-Image-....png). Read or open that file to show the user. - A failed run is not a protocol error — it comes back as a tool result
with
isError: trueand the failure message as text. Malformed arguments (unknown tool, unknown/missing/non-string argument) are rejected before anything is spent. - Inputs with a baked-in default can be omitted; only inputs listed in the
tool's
requiredarray must be provided.
Adding or changing noodles
The server loads graphs once at startup — the tool list never changes mid-session. To add or edit a tool:
- Build and test the workflow at nanoodle.com, press
💾, and save the downloaded
noodle-graph.jsoninto the configured noodles folder. The filename (minus.json, sanitized to[a-z0-9_-]) becomes the tool name. - Restart the MCP server (in Claude Code:
/mcp→ reconnect, or restart the session) to pick it up.
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.
- 10d ago First seen · 50 lines · 72 tokens per session scan A f7c50e4c94a9
noodles is a skill published in the GitHub repository nanoodlecom/nanoodle-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 72 tokens to every session and 667 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
image-generation
Optimizes image generation prompts using Subject-Context-Style structure. Use this skill when generating images, creating illustrations, photos, visual assets, editing images, or crafting prompts for any image generation model.
create-video-gift
Create and deliver a personalized video gift (photos + an original song) using the My Video Gift MCP tools. Use when the user wants to make a video gift, tribute or memorial film, anniversary/birthday/wedding video, or a personalized song film for someone.
post-to-xhs
A publishing guide for 小红书, a Chinese social-media platform. It covers posting image-and-text content or a longer formatted article, using supplied content or a webpage.
muapi-seedance-2
Expert Cinema Director skill for Seedance 2.0 (ByteDance) — high-fidelity video generation across Chinese, Global, and VIP tiers. Supports text-to-video, image-to-video, first-last-frame, omni reference, character training, omni-reference training, video editing, and watermark removal.
muapi-workflow
Build, run, and visualize multi-step AI generation workflows. The AI architect translates natural language descriptions into connected node graphs — chain image generation, video creation, enhancement, and editing into automated pipelines.
muapi-media-editing
Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more.