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.
curl -O https://raw.githubusercontent.com/jnMetaCode/ai-shortfilm-prompts/main/CLAUDE.mdgit clone --depth 1 https://github.com/jnMetaCode/ai-shortfilm-promptsWrote 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/jnmetacode/ai-shortfilm-prompts/claude-md)<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.
<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>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 | $0.00939 | $0.00939 |
| Opus 5 | $0.00469 | $0.00469 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
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.
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
-
File paths must be ASCII. No Chinese filenames. Chinese content goes in
*.zh.mdfiles. (Internal links broke twice before because docs linked to Chinese paths like方法论.mdthat don't exist — the real file ismethodology.zh.md.) -
Keep EN/中文 pairs in sync.
methodology,faq,credits,NOTICE, andtemplates/*each have an English file and a.zh.md(or.zh) sibling. Edit both, or note the divergence. -
The Skill:
SKILL.md(English) is what Claude Code loads and executes.SKILL.zh.mdis a human reference translation — keep it at parity when you change the rules, but the English file is canonical. Real skill files live atskills/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-promptis a symlink →../../skills/shortfilm-promptso a bare in-repoclaudestill 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.) -
After editing any internal link, run a dead-link check across all
*.mdbefore committing. This has bitten us repeatedly. -
X/tweet
statuslinks 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@PJaccetturohandle still links to his profile as attribution. The13.4M viewsstats table has a footnote crediting PJ Ace's tweet. Don't "fix" these back.
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.
- 12d ago First seen · 71 lines · 939 tokens per session scan A 6815ecec9b7f
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.
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.
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).
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).