ai-shortfilm-prompts: Instructions file for Claude Code

CLAUDE.md

ai-shortfilm-prompts CLAUDE.md is an instructions file for Claude Code from jnMetaCode/ai-shortfilm-prompts. It costs 939 tokens per session, scanned A, original, MIT.

Repository instructions for a bilingual English-and-Chinese documentation project and Claude Code skill for writing cinematic prompts for AI-generated videos.

In plain words
What is it for?
Editing the prompt library and skill, maintaining English and Chinese file pairs, and avoiding broken links or licensing mistakes.
Why use it?
They keep translated documents, file paths, licensing boundaries, and automated checks consistent.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is jnMetaCode/ai-shortfilm-prompts's own configuration. It tells Claude Code how to work on ai-shortfilm-prompts 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 ai-shortfilm-prompts configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jnMetaCode/ai-shortfilm-prompts. 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/jnMetaCode/ai-shortfilm-prompts/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jnMetaCode/ai-shortfilm-prompts

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 ai-shortfilm-prompts CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jnmetacode/ai-shortfilm-prompts/claude-md/github.svg)](https://agentmods.dev/instructions/jnmetacode/ai-shortfilm-prompts/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jnmetacode/ai-shortfilm-prompts/claude-md"><img src="https://agentmods.dev/badge/instructions/jnmetacode/ai-shortfilm-prompts/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 ai-shortfilm-prompts CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jnmetacode/ai-shortfilm-prompts/claude-md"><img src="https://agentmods.dev/badge/instructions/jnmetacode/ai-shortfilm-prompts/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 939 This file is loaded in full into every session.
When invoked 939 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 $0.00939 $0.00939
Opus 5 $0.00469 $0.00469
Sonnet 5 $0.00188 $0.00188
Haiku 4.5 $0.00094 $0.00094

Measured 12d ago against content hash 6815ecec9b7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ai-shortfilm-prompts 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 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.

CLAUDE.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Conventions for working in this repo. Read before editing.

What this repo is

A bilingual (EN/中文) methodology + prompt library + Claude Code Skill for writing cinematic AI-video prompts, built from Mx-Shell's Zombie Scavenger method. Pure docs + one Skill, no build step. Two CI checks: a dead-link scan (.github/workflows/links.yml) and LLM-judge skill evals (.github/workflows/evals.yml + evals/, needs the ANTHROPIC_API_KEY secret).

Hard conventions

  1. File paths must be ASCII. No Chinese filenames. Chinese content goes in *.zh.md files. (Internal links broke twice before because docs linked to Chinese paths like 方法论.md that don't exist — the real file is methodology.zh.md.)

  2. Keep EN/中文 pairs in sync. methodology, faq, credits, NOTICE, and templates/* each have an English file and a .zh.md (or .zh) sibling. Edit both, or note the divergence.

  3. The Skill: SKILL.md (English) is what Claude Code loads and executes. SKILL.zh.md is a human reference translation — keep it at parity when you change the rules, but the English file is canonical. Real skill files live at skills/shortfilm-prompt/ (plugin root), NOT .claude/skills/. A plugin only discovers skills under <plugin-root>/skills/; the old .claude/skills/ path made the marketplace install ship an empty plugin (fixed in v0.3.1). .claude/skills/shortfilm-prompt is a symlink → ../../skills/shortfilm-prompt so a bare in-repo claude still auto-discovers it as a project skill — single source of truth, two entry points. Don't move the real files back, don't delete the symlink, don't duplicate. (links.yml does NOT glob .claude/** so it won't double-scan the symlink with a wrong relative base.)

  4. After editing any internal link, run a dead-link check across all *.md before committing. This has bitten us repeatedly.

  5. X/tweet status links point to the maintainer's own tweet (x.com/aibuzhiyu/status/2056426660577288645), NOT PJ Ace's original — this is deliberate (don't drive traffic away). The @PJaccetturo handle still links to his profile as attribution. The 13.4M views stats table has a footnote crediting PJ Ace's tweet. Don't "fix" these back.

Read the full file on GitHub · 71 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 · 71 lines · 939 tokens per session scan A 6815ecec9b7f

Subscribe to this mod's changes

ai-shortfilm-prompts CLAUDE.md is an instructions file published in the GitHub repository jnMetaCode/ai-shortfilm-prompts (405 stars, last pushed 2d ago), licensed MIT. It adds 939 tokens to every session, about $0.0047 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.

Related

Other instructions, from other repositories

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 · 7,126 tokens

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

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

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