shooting-stars-meme-generator: Instructions file for Claude Code

CLAUDE.md

shooting-stars-meme-generator CLAUDE.md is an instructions file for Claude Code from TeKrop/shooting-stars-meme-generator. It costs 12,164 tokens per session, scanned A, original, MIT.

Project instructions for a single-page TypeScript site that recreates a shooting-stars meme with uploaded images, animation, and video export. TypeScript is JavaScript with optional type checks, and Bun is the runtime used to run and serve it.

In plain words
What is it for?
Use them when developing, configuring, building, serving, or exporting the site's animations as MP4, WebM, or GIF files.
Why use it?
They give an agent the project's architecture, tools, commands, and storage assumptions before it changes the code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is TeKrop/shooting-stars-meme-generator's own configuration. It tells Claude Code how to work on shooting-stars-meme-generator 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 shooting-stars-meme-generator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TeKrop/shooting-stars-meme-generator. 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/TeKrop/shooting-stars-meme-generator/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/TeKrop/shooting-stars-meme-generator

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 shooting-stars-meme-generator CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tekrop/shooting-stars-meme-generator/claude-md/github.svg)](https://agentmods.dev/instructions/tekrop/shooting-stars-meme-generator/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tekrop/shooting-stars-meme-generator/claude-md"><img src="https://agentmods.dev/badge/instructions/tekrop/shooting-stars-meme-generator/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 shooting-stars-meme-generator CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tekrop/shooting-stars-meme-generator/claude-md"><img src="https://agentmods.dev/badge/instructions/tekrop/shooting-stars-meme-generator/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12,164 This file is loaded in full into every session.
When invoked 12,164 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.12164 $0.12164
Opus 5 $0.06082 $0.06082
Sonnet 5 $0.02433 $0.02433
Haiku 4.5 $0.01216 $0.01216

Measured 10d ago against content hash 266bdd6621fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

shooting-stars-meme-generator CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **`docker-compose.yml`** — holds three services. `bun` runs production. It uses the default profile. Its healthcheck runs `bun -e` with a `fetch()` call. The `oven/bun:1` image carries no `wget` and no `curl`, unlike t
CLAUDE.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file gives guidance to Claude Code (claude.ai/code). Read it before you work with code in this repository.

What this is

This project is a single-page site. It recreates the "shooting stars" meme. A background video plays. Up to 6 images fly across the screen. The images move in time with fixed animation keyframes. The user uploads the images. The site shows the default doge image when the user uploads nothing.

The project uses no frontend framework. Bun is the runtime. Bun also bundles the CSS and the TypeScript. Bun serves HTTP. Bun gives hot module replacement in development mode. The project uses no database. The uploaded files on disk hold all of the state.

The code is TypeScript. Bun runs .ts files directly. Bun removes the types at load time. Bun writes no compiled files to disk.

The site can also export the animation as a video file. The server renders it with a native canvas and ffmpeg. It uses no headless browser. The output is MP4, WebM, or GIF. See server/export.ts in Architecture below.

Commands

Docker is the preferred workflow. Use just:

just build       # docker compose build
just start       # docker compose up -d. Production. Bun bundles, minifies, and caches at runtime.
just dev         # docker compose --profile dev up bun-dev. Live HMR through `bun --hot`.
just check       # tsc --noEmit, biome check, and the stars.css freshness check. Runs in the dev container.
just format      # biome check --write. Corrects lint and format problems.
just generate-css # Regenerates client/css/stars.css from server/keyframes.ts. See Architecture.
just up          # build, then start
just shell       # Opens a shell in the bun container.
just test        # bun test, in the dev container
just test-coverage # bun test --coverage, in the dev container
just down        # Stops and removes the containers. Keeps the volumes.
just down_clean  # Stops and removes the containers and the volumes.
just lock        # Regenerates bun.lock in the container.
just clean       # Prunes the Docker environment.

Read the full file on GitHub · 312 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 · 312 lines · 12,164 tokens per session scan A 266bdd6621fa

Subscribe to this mod's changes

shooting-stars-meme-generator CLAUDE.md is an instructions file published in the GitHub repository TeKrop/shooting-stars-meme-generator (24 stars, last pushed 7d ago), licensed MIT. It adds 12,164 tokens to every session, about $0.0608 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

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