higgsfield-skills: Instructions file for Claude Code

CLAUDE.md

higgsfield-skills CLAUDE.md is an instructions file for Claude Code from pixelab-ch/higgsfield-skills. It costs 3,994 tokens per session, scanned A, original, MIT.

Project instructions for a toolkit that helps Claude write prompts for Higgsfield, a platform for generating images and videos with AI models.

In plain words
What is it for?
Use it when building or maintaining skills for cinematic scenes, anime, product ads, real estate visuals, and other Higgsfield image or video jobs.
Why use it?
It removes the need to know which Higgsfield model and settings fit a creative request. It also defines the required format and project constraints for the toolkit.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is pixelab-ch/higgsfield-skills's own configuration. It tells Claude Code how to work on higgsfield-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything higgsfield-skills configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/USERNAME/.claude/skills/.

Reuse

Borrowing it

Nothing to install: this file belongs to pixelab-ch/higgsfield-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pixelab-ch/higgsfield-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/pixelab-ch/higgsfield-skills

Made for: Claude Code.

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 higgsfield-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pixelab-ch/higgsfield-skills/claude-md/github.svg)](https://agentmods.dev/instructions/pixelab-ch/higgsfield-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pixelab-ch/higgsfield-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/pixelab-ch/higgsfield-skills/claude-md/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 higgsfield-skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pixelab-ch/higgsfield-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/pixelab-ch/higgsfield-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,994 This file is loaded in full into every session.
When invoked 3,994 The same file — it is already loaded in full.
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 $0.03994 $0.03994
Opus 5 $0.01997 $0.01997
Sonnet 5 $0.00799 $0.00799
Haiku 4.5 $0.00399 $0.00399

Measured 10d ago against content hash d0393a2aa978, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

higgsfield-skills CLAUDE.md 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.

CLAUDE.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project

Higgsfield Skills — Multi-Model Prompt & Generation Toolkit

A collection of Claude Agent Skills that turn Claude into an expert prompt engineer for AI image and video generation on the Higgsfield platform. Each skill covers a creative style or use case (cinematic, anime, fight scenes, e-commerce ads, product 360°, real estate, etc.), produces a production-ready prompt, maps it to the most appropriate Higgsfield model, and can optionally submit the generation directly through the Higgsfield MCP server. It is the rearchitecture of the existing higgsfield-seedance2-jineng repo, which today only targets a single model (Seedance 2.0) and only outputs static prompt text.

Core Value: Given a creative request, Claude produces a model-correct, spec-accurate prompt and (on explicit confirmation) generates the asset on Higgsfield — without the user needing to know which of the ~38 Higgsfield models to pick or what parameters each accepts.

Constraints

  • Platform: Higgsfield only — all generation goes through the Higgsfield MCP server already present in the environment
  • Compatibility: Must follow the Claude Agent Skills format (YAML frontmatter name + description; SKILL.md + optional references/) so skills load in both Claude Code and Desktop
  • Cost: Generation consumes Higgsfield credits → never generate without explicit user confirmation
  • Accuracy: Per-model specs must match what models_explore reports, not invented numbers
  • Languages: English + French only
  • Source of truth for model constraints: the live models_explore catalogue, not hardcoded assumptions that can drift

Technology Stack

1. SKILL.md Frontmatter Specification

Required fields

Field Required Limit Rules
name Recommended (not strictly required — defaults to directory name) 64 chars Lowercase letters, numbers, hyphens only. No XML tags. Reserved words "anthropic" and "claude" forbidden. Must match the directory name when set.
description Recommended 1024 chars Non-empty. No XML tags. Write in third person. Include what it does AND when to use it. Put key use case first — combined description + when_to_use is truncated to 1,536 chars in the skill listing.

Read the full file on GitHub · 267 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. 10d ago First seen · 267 lines · 3,994 tokens per session scan A d0393a2aa978

Subscribe to this mod's changes

higgsfield-skills CLAUDE.md is an instructions file published in the GitHub repository pixelab-ch/higgsfield-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 3,994 tokens to every session, about $0.0200 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens