Borrowing it
Nothing to install: this file belongs to OSideMedia/higgsfield-ai-prompt-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/OSideMedia/higgsfield-ai-prompt-skill/main/CLAUDE.mdgit clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skillWrote 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/instructions/osidemedia/higgsfield-ai-prompt-skill/claude-md)<a href="https://agentmods.dev/instructions/osidemedia/higgsfield-ai-prompt-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/osidemedia/higgsfield-ai-prompt-skill/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.
<a href="https://agentmods.dev/instructions/osidemedia/higgsfield-ai-prompt-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/osidemedia/higgsfield-ai-prompt-skill/claude-md.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 | $0.01353 | $0.01353 |
| Opus 5 | $0.00677 | $0.00677 |
| Sonnet 5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
higgsfield-ai-prompt-skill 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 11d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
Higgsfield AI Prompt Skill — a Cowork skill library for generating high-quality prompts for Higgsfield's video and image AI models. Includes model selection guides, cinematic vocabulary, prompt examples, genre templates, and a learning memory system.
Tech Stack
- Skill format: Cowork SKILL.md with YAML frontmatter
- Scripts: Python 3 (no dependencies beyond stdlib)
- Data: JSON databases in
db/ - Docs: Markdown throughout
Directory Structure
SKILL.md ← Main dispatcher (routes to sub-skills — start here)
DISCIPLINE.md ← Operating discipline (cites HARD RULES by number)
model-guide.md ← Video + image model comparison tables
image-models.md ← Image model specs, UI controls, pricing
vocab.md ← Camera movement + cinematic vocabulary
prompt-examples.md ← Production prompt examples by genre
photodump-presets.md ← 29 Photodump style presets
production-benchmarks.md ← Iteration/cost benchmarks referenced by templates
scripts/ ← Python tooling (run from the repo root)
├── validate.py ← Pre-release health checks (--strict for releases)
├── higgsfield_memory.py ← DB operations for learning memory
├── seedance_lint.py ← Seedance preflight linter
├── sync_specs.py ← Regenerates specs/ from a models_explore snapshot
├── refresh_specs.py ← Spec-drift tripwire (live CLI vs specs/cli_baseline.json)
├── generate_user_guide.py ← Release PDF generator (+ validate_user_guide.py,
│ sub_skill_descriptions.py)
└── build_index.py ← Regenerates INDEX.md + checks QUICK FACTS anchors
specs/ ← Machine-readable model specs (generated — never hand-edit;
video + image + audio, each generated from a dated
models_explore snapshot)
INDEX.md ← Generated heading index of every SKILL.md
tests/ ← pytest suite for the Python tooling (CI-run)
evals/ ← Behavioral eval cases + run_evals.py (CI-run)
skills/ ← 32 sub-skill directories + shared/
templates/ ← 10 genre templates + ad-asset-prep.md,
character-design/ (6), seedance/ (9), text-overlays/ (3)
db/ ← Filter + quality memory JSON databases
db/ledger/ ← Generation ledger (one append-only file per project;
_global.json generated; see db/ledger/README.md)
docs/ ← Extended reference documents
workspace/ ← Git-ignored working area (input/ → processed/, output/)
.claude/
├── settings.json ← Permission rules
├── rules/ ← Thin pointers to root reference files (no duplication)
└── commands/ ← /validate, /release
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.
- 11d ago First seen · 78 lines · 1,353 tokens per session scan A d9e6cef6eba1
higgsfield-ai-prompt-skill CLAUDE.md is an instructions file published in the GitHub repository OSideMedia/higgsfield-ai-prompt-skill (529 stars, last pushed 19d ago), licensed MIT. It adds 1,353 tokens to every session, about $0.0068 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 2026-08-30.
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.
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.
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).
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.
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.
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).