novelai-workflows

novelai-workflows is a skill for Claude Code, Codex from xinvxueyuan/NovelAI-Image-MCP. It costs 45 tokens per session (4,199 once invoked), scanned A, original, MIT.

A set of instructions for chaining NovelAI image tools into multi-step workflows. NovelAI is an image-generation service that can create, edit, annotate, and enlarge images.

In plain words
What is it for?
Use it to build pipelines such as text-to-image followed by upscaling, annotation, image-to-image editing, or Director edits.
Why use it?
It provides an ordered recipe for combining separate image operations when one generation or edit is not enough.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for cline. Also seen: built for cline.

Good fit Use it to build pipelines such as text-to-image followed by upscaling, annotation, image-to-image editing, or Director edits.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xinvxueyuan/novelai-image-mcp/novelai-workflows
Install

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.

Any agent
npx skills add xinvxueyuan/NovelAI-Image-MCP --skill novelai-workflows
Clone the repo
git clone --depth 1 https://github.com/xinvxueyuan/NovelAI-Image-MCP

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for novelai-workflows

README.md
[![agentmods](https://agentmods.dev/badge/skills/xinvxueyuan/novelai-image-mcp/novelai-workflows/github.svg)](https://agentmods.dev/skills/xinvxueyuan/novelai-image-mcp/novelai-workflows)
Your own site
<a href="https://agentmods.dev/skills/xinvxueyuan/novelai-image-mcp/novelai-workflows"><img src="https://agentmods.dev/badge/skills/xinvxueyuan/novelai-image-mcp/novelai-workflows/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.

agentmods 80×15 button for novelai-workflows

Your own site · 80×15
<a href="https://agentmods.dev/skills/xinvxueyuan/novelai-image-mcp/novelai-workflows"><img src="https://agentmods.dev/badge/skills/xinvxueyuan/novelai-image-mcp/novelai-workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,199 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.04199
Opus 5 $0.00023 $0.02099
Sonnet 5 $0.00009 $0.00840
Haiku 4.5 $0.00005 $0.00420

Measured 12d ago against content hash ca91883cb046, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

novelai-workflows 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 12d 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.

skills/novelai-workflows/SKILL.md · 336 lines

How it starts

The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.

novelai-workflows

Instructions for the agent to follow when chaining NovelAI tools into multi-step creative pipelines.

When to use

Use this skill when the user asks for a multi-step image pipeline or workflow recipe — e.g. generate then upscale for higher resolution, build a ControlNet-style pipeline (txt2img → annotate → img2img), apply Director edits to an existing image (img2img → director), or run a full end-to-end production flow (txt2img → director → upscale). It covers how to wire the 11 NovelAI MCP tools and the matching CLI commands into chains. For individual tool parameters, see the novelai-mcp-tools skill; for CLI flags, see the novelai-cli skill — do not duplicate those references here.

Instructions

Prerequisites

  • Credentials configured: NOVELAI_TOKEN (preferred) or NOVELAI_USERNAME + NOVELAI_PASSWORD.
  • Output directory writable: NOVELAI_OUTPUT_DIR (default outputs), or pass -o <dir> per CLI invocation.
  • MCP: a connected MCP host (Claude Desktop, Cline, or mcp dev apps/server/dev_server.py). CLI: novelai-image-mcp on PATH (or uvx novelai-image-mcp, or uv run --directory apps/server novelai-image-mcp).
  • Check Anlas balance before expensive chains — call get_subscription (MCP) or novelai-image-mcp info (CLI) first. Upscale and Director tools cost Anlas proportional to source resolution.
  1. txt2img → upscale — generate then upscale for higher resolution.

    Goal: generate an image, then upscale it for higher resolution than the generator produces natively.

    When to use: you need a final image larger than the model's native output, or you want to refine detail on a low-step draft before committing Anlas to a full-resolution render.

    MCP sequence:

    1. generate_image(prompt="...", width=832, height=1216, seed=42) → returns ImageContent + path like outputs/generate-<ts>.png.
    2. Read that PNG, base64-encode it, and call upscale_image(image="<base64>", factor=4) → returns the 4× PNG (outputs/upscale-<ts>.png).

Read the full file on GitHub · 336 lines

Changes

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.

  1. 12d ago First seen · 336 lines · 45 tokens per session scan A ca91883cb046

Subscribe to this mod's changes

novelai-workflows is a skill published in the GitHub repository xinvxueyuan/NovelAI-Image-MCP (4 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 4,199 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 2026-08-31.