What is AI-MarkDone copilot-instructions.md?

Repository instructions for a browser extension that improves copying Markdown from ChatGPT and Gemini. They describe how the extension handles formulas, tables, code, multiple websites, and isolated interface components.

Use them when adding support for a website, changing content extraction or Markdown conversion, or updating the extension's toolbar and dialogs.

They show the agent where platform-specific behavior belongs and how to avoid conflicts with the pages the extension modifies.

How zhaoliangbin42/AI-MarkDone configures GitHub Copilot

Reuse

Borrowing it

Nothing to install: this file belongs to zhaoliangbin42/AI-MarkDone. 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/zhaoliangbin42/AI-MarkDone/main/.github/copilot-instructions.md

Clone the repo

git clone --depth 1 https://github.com/zhaoliangbin42/AI-MarkDone

Made for: GitHub Copilot.

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/zhaoliangbin42/ai-markdone/copilot-instructions/github.svg)](https://agentmods.dev/instructions/zhaoliangbin42/ai-markdone/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/zhaoliangbin42/ai-markdone/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/zhaoliangbin42/ai-markdone/copilot-instructions/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/zhaoliangbin42/ai-markdone/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/zhaoliangbin42/ai-markdone/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,337 This file is loaded in full into every session.

When invoked 1,337 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	$0.01337	$0.01337
Opus 5.5	$0.00535	$0.00535
Sonnet 5.5	$0.00267	$0.00267
Haiku 4.5	$0.00134	$0.00134

Measured 2mo ago against content hash daee12f79332, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AI-MarkDone copilot-instructions.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.

.github/copilot-instructions.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Copy Enhance - AI Coding Agent Instructions

Project Overview

Chrome Extension (Manifest V3) that enhances ChatGPT/Gemini with robust Markdown export. Extracts LaTeX from KaTeX, handles rendering failures, converts tables/code to Markdown, and provides click-to-copy math formulas.

Architecture Patterns

Adapter Pattern for Multi-Platform Support

Registry: src/content/adapters/registry.ts manages platform adapters
Base: SiteAdapter abstract class defines interface (selectors, HTML extraction, streaming detection)
Implementations: ChatGPTAdapter, GeminiAdapter (each 100 lines)
Critical: New platforms extend SiteAdapter and register in AdapterRegistry constructor
Adapters provide DOM selectors specific to each platform's structure

Shadow DOM Isolation

All UI components use Shadow DOM to avoid CSS conflicts with host pages
See src/content/components/toolbar.ts, modal.ts - each creates shadow root and injects styles
Styles defined in src/styles/*.css.ts as template literals for Shadow DOM injection
Toolbar: Icon-only buttons with hover tooltips, auto-updating word/char count on right
Never use global CSS - it won't reach Shadow DOM components

Parser Pipeline Architecture

MarkdownParser orchestrates specialized extractors in sequence:

CodeExtractor: <pre><code> → fenced code blocks with language tags
TableParser: HTML tables → Markdown pipes
Turndown: HTML → Markdown (with custom rules for KaTeX)
Post-processing: Cleanup and normalization

Critical: Math formulas are handled by Turndown rules that extract LaTeX from <annotation encoding="application/x-tex"> tags.

MutationObserver Pattern

src/observers/mutation-observer.ts watches for new messages with 200ms debounce
Uses WeakSet to track processed messages (avoid duplicate toolbars)
Container selection: tries multiple selectors (main, main > div, etc.) - see getObserverContainer()

Read the full file on GitHub · 106 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 · 106 lines · 1,337 tokens per session scan A daee12f79332

Subscribe to this mod's changes

AI-MarkDone copilot-instructions.md is an instructions file published in the GitHub repository zhaoliangbin42/AI-MarkDone (208 stars, last pushed 8d ago), licensed MIT. It adds 1,337 tokens to every session, about $0.0053 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.

chatgpt chrome-extension claude deepseek gemini markdown

AI-MarkDone copilot-instructions.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
AI-MarkDone copilot-instructions.mdzhaoliangbin42/AI-MarkDone	Instructions file	208	8d ago	MIT	A	1,337	GitHub Copilot
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

AI-MarkDone: Instructions file for GitHub Copilot