ChatCrystal: Instructions file for Codex

AGENTS.md

ChatCrystal AGENTS.md is an instructions file for Codex, OpenCode from ZengLiangYi/ChatCrystal. It costs 3,013 tokens per session, scanned A, original, Apache-2.0.

Project instructions for ChatCrystal, an application that turns AI coding conversations into searchable notes. It covers the project structure, development commands, ports, builds, and desktop packaging.

In plain words
What is it for?
Use it when working on ChatCrystal’s server, client, production build, or Electron desktop release.
Why use it?
It gives a coding agent the repository context and the commands needed to develop, test, build, and run the application.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; reads ~/.codex paths.

This is ZengLiangYi/ChatCrystal's own configuration. It tells Codex and OpenCode how to work on ChatCrystal 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 ChatCrystal configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ZengLiangYi/ChatCrystal. 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/ZengLiangYi/ChatCrystal/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ZengLiangYi/ChatCrystal

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.

agentmods badge for ChatCrystal AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zengliangyi/chatcrystal/agents-md/github.svg)](https://agentmods.dev/instructions/zengliangyi/chatcrystal/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zengliangyi/chatcrystal/agents-md"><img src="https://agentmods.dev/badge/instructions/zengliangyi/chatcrystal/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.

agentmods 80×15 button for ChatCrystal AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zengliangyi/chatcrystal/agents-md"><img src="https://agentmods.dev/badge/instructions/zengliangyi/chatcrystal/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,013 This file is loaded in full into every session.
When invoked 3,013 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 $0.03013 $0.03013
Opus 5.5 $0.01205 $0.01205
Sonnet 5.5 $0.00603 $0.00603
Haiku 4.5 $0.00301 $0.00301

Measured 1mo ago against content hash e392778b39db, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ChatCrystal 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 1mo 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 · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

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

Project Overview

ChatCrystal is an AI conversation knowledge crystallization tool. It imports conversations from AI coding tools (Claude Code, Cursor, Codex CLI, Trae, GitHub Copilot), uses LLM to generate structured notes (title, summary, key conclusions, code snippets, tags), and provides semantic search via embeddings. The UI is in Simplified Chinese.

Commands

# Install (Node.js 24; root workspace uses pnpm via Corepack)
corepack enable
pnpm install

# Development (server port 3721 + client port 13721)
pnpm dev

# Build for production
pnpm build

# Production server (serves frontend statically on port 3721)
pnpm start

# Electron desktop app
pnpm dev:electron        # dev mode (Vite HMR + Electron window)
pnpm build:electron      # build NSIS installer → release/
pnpm pack:electron       # build unpacked directory (faster for testing)

# Release (bump version + git tag + push → CI builds & publishes)
pnpm release             # patch bump (0.1.0 → 0.1.1)
pnpm release -- minor    # minor bump
pnpm release -- major    # major bump
pnpm release -- 1.0.0    # explicit version
pnpm release:electron -- 1.0.1  # Electron-only release → electron-v*
pnpm release:npm -- 1.0.1       # npm-only release → npm-v*

# Lint
pnpm lint
pnpm lint:fix

# Tests (all layers by default)
pnpm test
pnpm test:server
pnpm test:client
pnpm test:electron
pnpm --filter ./server smoke:mcp  # requires pnpm build first

# Dependency security
pnpm security:audit
pnpm security:signatures

Release Tag Semantics

Use scripts/release.mjs for releases; do not manually bump versions, commit, tag, and push unless the user explicitly asks for a custom recovery flow.

  • v* tags are full releases and trigger both npm publishing and Electron GitHub Release builds. Use this only when both root package.json and server/package.json should move together.
  • electron-v* tags are Electron-only releases. Use pnpm release:electron -- <version> for desktop-only changes, including Electron main/preload/tray/packaging changes and Electron-gated client UI.
  • npm-v* tags are npm-only releases. Use pnpm release:npm -- <version> for CLI/server/MCP package changes.
  • The published npm package version comes from server/package.json, not the root package. If a v* tag is pushed while server/package.json still points at an already-published version, the npm job will fail with E403 You cannot publish over the previously published versions.
  • If an Electron-only release is accidentally published with a v* tag and the Electron job succeeds but npm fails because the server version already exists, do not delete or re-tag the release by default. Treat the GitHub Release as usable, document the cause, and use electron-v* for the next Electron-only release.

Read the full file on GitHub · 215 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. 1mo ago Changed · +15 lines · +91 tokens per session e392778b39db
  2. 1mo ago Changed · +10 tokens per session fa5326a46486
  3. 1mo ago First seen · 200 lines · 2,912 tokens per session scan A 39592263145f

Subscribe to this mod's changes

ChatCrystal AGENTS.md is an instructions file published in the GitHub repository ZengLiangYi/ChatCrystal (61 stars, last pushed 2d ago), licensed Apache-2.0. It adds 3,013 tokens to every session, about $0.0121 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.

Related

Other instructions, from other repositories