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.
curl -O https://raw.githubusercontent.com/Bloodshed-Rain/TheMAGI/main/AGENTS.mdgit clone --depth 1 https://github.com/Bloodshed-Rain/TheMAGIWrote 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/bloodshed-rain/themagi/agents-md)<a href="https://agentmods.dev/instructions/bloodshed-rain/themagi/agents-md"><img src="https://agentmods.dev/badge/instructions/bloodshed-rain/themagi/agents-md.svg" alt="Measured on agentmods" 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 | $0.00599 | $0.00599 |
| Opus 5 | $0.00300 | $0.00300 |
| Sonnet 5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
TheMAGI AGENTS.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 2d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/main/ contains Electron main-process code and IPC handlers, src/preload/ exposes the bridge API, and src/renderer/ holds the Vite + React UI (pages/, components/, styles/, assets/). Core replay parsing, stats, and import logic live in top-level src/ modules plus src/pipeline/. Tests live in tests/*.test.ts. Static marketing assets are under site/, screenshots under screenshots/, and character art in CharacterCards/.
Build, Test, and Development Commands
Use Node.js 18+ and install with npm install.
npm run devstarts the Vite renderer, compiles main/preload TS, and launches Electron.npm run buildcreates a packaged app inrelease/; usebuild:win,build:mac, orbuild:linuxfor platform-specific builds.npm testruns the Vitest suite once;npm run test:watchkeeps tests running during development.npm run lintcheckssrc/with ESLint;npm run lint:fixapplies safe fixes.npm run formatandnpm run format:checkrun Prettier onsrc/**/*.{ts,tsx}.
Create key.env from .env.example when working with AI features or packaging.
Coding Style & Naming Conventions
TypeScript is strict and React uses function components. Follow Prettier defaults in this repo: 2-space indentation, semicolons, double quotes, trailing commas, and printWidth: 120. Use PascalCase for React components and page files (Dashboard.tsx), camelCase for utilities (playerSummary.ts), and keep test files in name.test.ts form. Prefer small modules near their owning layer instead of cross-cutting helpers.
Testing Guidelines
Vitest looks for tests/**/*.test.ts with global APIs enabled. Add or update tests when changing parsing, importer, DB, config, or pipeline behavior. There is no enforced coverage threshold, so contributors should cover new branches and regression-prone paths explicitly. Run npm test before opening a PR.
Commit & Pull Request Guidelines
Recent history uses short imperative subjects such as Fix Dolphin playback... and Update landing page.... Keep commit messages concise, capitalized, and focused on one change. PRs should include a clear summary, testing notes, linked issues when relevant, and screenshots/GIFs for UI changes in src/renderer/ or site/.
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.
- 2d ago First seen · 28 lines · 599 tokens per session scan A 86bb6d6f6b99
TheMAGI AGENTS.md is an instructions file published in the GitHub repository Bloodshed-Rain/TheMAGI (8 stars, last pushed 11d ago), licensed MIT. It adds 599 tokens to every session, about $0.0030 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.
Other instructions, from other repositories
vibetags com-example-service-NewAnnotationsShowcase-SandboxTestHelper.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for sandboxtesthelper and sandbox restriction.
agent-compass backoffice.instructions.md
Use when modifying the React backoffice in apps/backoffice, including TanStack Router routes, React Query flows, MUI UI, and Vitest tests.
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).
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.
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.