What is crystal AGENTS.md?

A development guide for Stravu Crystal, a desktop application built with Electron, React, and TypeScript. It explains the monorepo structure, where each part of the app lives, and how to build, test, and package it.

Use it when working on the Electron main process, React frontend, shared code, assets, packaging, type checks, or end-to-end tests.

A monorepo stores multiple related parts of a project together, so the guide helps you change the correct package and run the right checks.

How stravu/crystal configures Codex and OpenCode

About the project

Crystal was a desktop application for running multiple Codex and Claude Code sessions in parallel Git worktrees and comparing their coding work, but it was deprecated in February 2026 and replaced by Nimbalyst. It was intended for developers managing parallel AI-assisted development sessions. The catalogue contains instructions related to the former Crystal workflow.

stravu/crystal · 3,127 stars · on GitHub · nimbalyst.com

Reuse

Borrowing it

Nothing to install: this file belongs to stravu/crystal. 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/stravu/crystal/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/stravu/crystal

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/stravu/crystal/agents-md/github.svg)](https://agentmods.dev/instructions/stravu/crystal/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/stravu/crystal/agents-md"><img src="https://agentmods.dev/badge/instructions/stravu/crystal/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/stravu/crystal/agents-md"><img src="https://agentmods.dev/badge/instructions/stravu/crystal/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 702 This file is loaded in full into every session.

When invoked 702 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.

Model	Per session	Once invoked
Fable 5.1	$0.00702	$0.00702
Opus 5.5	$0.00281	$0.00281
Sonnet 5.5	$0.00140	$0.00140
Haiku 4.5	$0.00070	$0.00070

Measured 2mo ago against content hash 040af1ff70a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

crystal 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 2mo 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.

AGENTS.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

Root pnpm workspace with packages: main/ (Electron main process, TypeScript), frontend/ (React + Vite), shared/ (shared types), and tests/ (Playwright E2E).
Key paths: main/src/{services,ipc,utils}/, frontend/src/{components,hooks,stores,utils}/, main/assets/, scripts/.
Build artifacts: frontend/dist/, main/dist/, packaged output dist-electron/.

Build, Test, and Development Commands

Dev app: pnpm dev (spawns frontend + Electron).
Build all: pnpm build (frontend, main, then electron package).
Package (examples): pnpm build:mac, pnpm build:linux.
Lint: pnpm lint; Type-check: pnpm typecheck (runs per package).
Tests (E2E): pnpm test, pnpm test:ui, CI configs in playwright.ci*.config.ts.
Main unit tests (if added): pnpm --filter main test, coverage: pnpm --filter main run test:coverage.

Coding Style & Naming Conventions

Use TypeScript throughout; follow ESLint configs in frontend/eslint.config.js and main/eslint.config.js.
Indentation 2 spaces; prefer explicit types at module boundaries.
Naming: camelCase for variables/functions, PascalCase for React components/types, kebab-case for filenames (React files may match component name).
Run pnpm lint && pnpm typecheck before sending PRs.

Testing Guidelines

E2E tests live in tests/*.spec.ts (Playwright). Example: pnpm test -- tests/smoke.spec.ts.
Add Playwright tests for user-visible flows; mock external services where possible.
For backend logic in main/, use Vitest colocated under main/src/**/__tests__ or *.spec.ts.

Commit & Pull Request Guidelines

Commits: present tense, focused, reference issues (e.g., "Fix session diff flicker, closes #123").
PRs must include: clear description, linked issues, testing notes; screenshots/GIFs for UI changes.
If dependencies change, run pnpm run generate-notices and commit updated NOTICES.

Security & Configuration Tips

Node >= 22.14; pnpm >= 8. Use pnpm only.
Secrets via .env (dotenv) for local dev; never commit secrets.
To avoid clobbering local data when hacking on Crystal with Crystal: CRYSTAL_DIR=~/.crystal_test pnpm dev.

Read the full file on GitHub · 43 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.

2mo ago First seen · 43 lines · 702 tokens per session scan A 040af1ff70a1

Subscribe to this mod's changes

crystal AGENTS.md is an instructions file published in the GitHub repository stravu/crystal (3,127 stars, last pushed 8mo ago), licensed MIT. It adds 702 tokens to every session, about $0.0028 per session on Opus 5.5. 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.

agentic-ai ai ai-coding anthropic development-environment vibe-coding

crystal AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
crystal AGENTS.mdstravu/crystal	Instructions file	3.1k	8mo ago	MIT	A	702	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

crystal: Instructions file for Codex