agentmods.dev

TheMAGI: Instructions file for Claude Code

CLAUDE.md

TheMAGI CLAUDE.md is an instructions file for Claude Code from Bloodshed-Rain/TheMAGI. It costs 3,439 tokens per session, scanned A, original, MIT.

A repository instruction file for an Electron and React desktop app that analyses Super Smash Bros. Melee replay files and generates coaching feedback with language models. It documents the project structure, commands, build process, and import pipeline.

In plain words
What is it for?
Use it to develop, build, package, or run the app, including importing replay folders and analysing individual replay files.
Why use it?
It gives a coding agent the project context and exact development commands needed to work in this repository. It also records platform build and data-import details that are not obvious from the file name alone.

Instructions file for Claude Code

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

This is Bloodshed-Rain/TheMAGI's own configuration. It tells Claude Code how to work on TheMAGI 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 TheMAGI configures →

not rated 8repo 13d ago A scan 3,439 tokens original MIT
View source ↗ Bloodshed-Rain/TheMAGI themagi.gg
Reuse

Borrowing it

Nothing to install: this file belongs to Bloodshed-Rain/TheMAGI. 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/Bloodshed-Rain/TheMAGI/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Bloodshed-Rain/TheMAGI

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 TheMAGI CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bloodshed-rain/themagi/claude-md/github.svg)](https://agentmods.dev/instructions/bloodshed-rain/themagi/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bloodshed-rain/themagi/claude-md"><img src="https://agentmods.dev/badge/instructions/bloodshed-rain/themagi/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 TheMAGI CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bloodshed-rain/themagi/claude-md"><img src="https://agentmods.dev/badge/instructions/bloodshed-rain/themagi/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,439 This file is loaded in full into every session.
When invoked 3,439 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 $0.03439 $0.03439
Opus 5 $0.01720 $0.01720
Sonnet 5 $0.00688 $0.00688
Haiku 4.5 $0.00344 $0.00344

Measured 4d ago against content hash b699feab15be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

TheMAGI 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 4d 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 · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

MAGI (Melee Analysis through Generative Intelligence) is an Electron + React desktop app that analyzes Super Smash Bros. Melee replays (.slp files via slippi-js) and generates AI coaching feedback via LLM providers.

Commands

  • Install: npm install then npx electron-rebuild (rebuilds better-sqlite3 and koffi against the Electron ABI — required before npm run dev will boot)
  • Dev mode: npm run dev — runs scripts/dev.js: compiles main/preload via tsc -p tsconfig.main.json, starts the Vite renderer server, then spawns Electron with VITE_DEV_SERVER_URL set. Also auto-loads key.env into process.env.
  • Build: npm run build — compiles main process TS, builds renderer via Vite, packages with electron-builder
  • Platform builds: npm run build:linux, build:win, build:mac
  • Run pipeline CLI: npx tsx src/pipeline-cli.ts <file.slp> [--target player] [--json]
  • Run import CLI: npx tsx src/import-cli.ts <folder> [--target player] (bulk-imports a folder into the local DB)
  • Backfill per-instance events: ELECTRON_RUN_AS_NODE=1 npx electron --require tsx/cjs src/backfill-cli.ts [--force] [--limit N] — re-parses already-imported replays to fill the v10-v14 event tables. Must run through Electron's node when better-sqlite3 is electron-rebuilt (plain npx tsx hits a NODE_MODULE_VERSION error); the CLI prints this hint on failure. Idempotent per game (delete + reinsert in one transaction); re-hashes files so moved/replaced replays are skipped, never misattributed.
  • Type-check main process: npx tsc -p tsconfig.main.json --noEmit
  • Run tests: npm test — runs Vitest once over tests/**/*.test.ts
  • Single test file: npx vitest run tests/pipeline.test.ts (or pass a name pattern: npx vitest run -t "neutral win rate")
  • Watch tests: npm run test:watch
  • Lint / format: npm run lint (ESLint), npm run lint:fix, npm run format (Prettier write), npm run format:check

Read the full file on GitHub · 125 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. 4d ago First seen · 125 lines · 3,439 tokens per session scan A b699feab15be

Subscribe to this mod's changes

TheMAGI CLAUDE.md is an instructions file published in the GitHub repository Bloodshed-Rain/TheMAGI (8 stars, last pushed 13d ago), licensed MIT. It adds 3,439 tokens to every session, about $0.0172 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 2026-09-04.

Building agentsGame developmentaiai-toolscoachingelectronlocal-firstmelee
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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens