Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/tt-a1i/chat_edit/claude-mdgit clone --depth 1 https://github.com/tt-a1i/chat_editWrote 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/tt-a1i/chat_edit/claude-md)<a href="https://agentmods.dev/instructions/tt-a1i/chat_edit/claude-md"><img src="https://agentmods.dev/badge/instructions/tt-a1i/chat_edit/claude-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 | $0.03512 | $0.03512 |
| Opus 5 | $0.01756 | $0.01756 |
| Sonnet 5 | $0.00702 | $0.00702 |
| Haiku 4.5 | $0.00351 | $0.00351 |
Grade A, and why
chat_edit 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 5d 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 — 417 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.
Language Preference
请使用中文回复所有对话和代码注释。 All responses, explanations, and code comments should be in Chinese (Simplified).
Project Background
当前状态: 这是一个处于持续开发阶段的项目，代码库正在进行重构和优化。
Skill 使用规范
- 页面开发或 UI 修改时：使用
frontend-designskill - 代码审查时：使用
code-review-excellenceskill
Project Overview
A dual-mode AI application combining:
- Chat Scene: Traditional conversational AI interface with streaming responses
- AI Editing Scene: Rich text editor (Quill) with AI-powered text manipulation features
Built with Vue 3 + TypeScript + Vite, using Moonshot AI API for LLM capabilities.
Development Commands
# Development server
bun dev
# Build (includes TypeScript type checking)
bun build
# Preview production build
bun preview
# Linting
bun lint
bun lint:fix
# Type checking
bun typecheck
# Testing
bun test # Unit tests (watch mode)
bun test:run # Unit tests (single run)
bun test:coverage # Unit tests with coverage
bun test:ui # Vitest UI
bun test:e2e # E2E tests
bun test:e2e:ui # Playwright UI
bun test:all # Run all tests
Package Manager: This project uses bun (version 1.2.14 specified in package.json).
Testing: 详见 TESTING.md 查看完整测试指南。
Architecture
Scene Management
The app operates in two distinct scenes controlled by services/appConfig.ts:
SCENES.CHAT // Traditional chat interface
SCENES.AI_EDITING // Rich text editor with AI features
Scene switching happens through switchScene() which updates currentScene.value and manages panel visibility.
Data Flow Architecture
Chat Scene Flow:
- User input →
addUserMessage()inservices/chat.ts - Empty AI message created with
isStreaming: true useAI.generate()→useApi.generateChat()→ SSE stream processing- Incremental updates via
handleAiPartialResponse() - Completion via
handleAiCompletion()setsisStreaming: false
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.
- 5d ago First seen · 417 lines · 3,512 tokens per session scan A 36b9e3db6876
chat_edit CLAUDE.md is an instructions file published in the GitHub repository tt-a1i/chat_edit (21 stars, last pushed 6mo ago), licensed MIT. It adds 3,512 tokens to every session, about $0.0176 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 2026-08-30.
Other instructions, from other repositories
claude-chat-exporter CLAUDE.md
Instructions for agarwalvishal/claude-chat-exporter, covering claude.md, what this is, core design decision, how the export works and the install page & bookmarklet (docs/index.html).
AionUi AGENTS.md
AGENTS.md instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
core copilot-instructions.md
Copilot instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
telegramify-markdown AGENTS.md
Instructions for sudoskys/telegramify-markdown, covering telegramify-markdown agent guide, task routing, quick commands, project rules and architecture map.