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/luanjunyi/opuspad/agents-mdgit clone --depth 1 https://github.com/luanjunyi/opuspadWhat 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 | $0.00563 | $0.00563 |
| Opus 5 | $0.00282 | $0.00282 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
opuspad 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 yesterday.
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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repository is currently spec-first. Start with .spec/design-doc-md-editor-chrome.md for architecture, task scope, and manual verification steps. Use .spec/tracker.md to track task status and .spec/escalations.md for blockers that need a decision. The application scaffold has not been committed yet; when Task 1 lands, keep runtime code in src/, shared file-system logic in src/services/, UI pieces in src/components/, and treat dist/ as generated build output.
Build, Test, and Development Commands
There are no checked-in build scripts yet because the extension scaffold is still pending. Once Task 1 is implemented, standard commands should be:
-
npm install: install Vite, React, and extension dependencies. -
npm run dev: start the local development server for UI work. -
npm run build: create the unpacked Chrome extension bundle indist/.
Until those scripts exist, use the verification steps in .spec/design-doc-md-editor-chrome.md as the executable source of truth.
Coding Style & Naming Conventions
The design doc targets React 18, TypeScript 5, Vite 5, Manifest V3, CodeMirror, and BlockNote. Follow a simple layout: 2-space indentation, PascalCase for React components (MarkdownEditor.tsx), camelCase for functions and hooks (mountWorkspace), and kebab-case only for non-code asset names when needed. Keep file-system access code isolated from UI code, and prefer small modules over large mixed-purpose files.
Testing Guidelines
No automated test framework is committed yet. For now, every change must pass the manual checks in the design doc, especially Chrome extension loading, workspace mounting, and debounced file saves. When tests are added, prefer *.test.ts and *.test.tsx files near the code they cover or under tests/, and focus first on src/services/fileSystem.ts, editor routing, and save behavior.
Commit & Pull Request Guidelines
This repository has no established commit history yet, so set the baseline now: use short imperative commit subjects such as Add extension scaffold or Implement file tree sidebar. Keep each commit focused on one task from .spec/tracker.md. Pull requests should name the task addressed, summarize behavior changes, list verification steps performed, and include screenshots or a short video for UI 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.
- yesterday First seen · 34 lines · 563 tokens per session scan A 18083229ff3b
opuspad AGENTS.md is an instructions file published in the GitHub repository luanjunyi/opuspad (2 stars, last pushed 3mo ago), licensed ISC. It adds 563 tokens to every session, about $0.0028 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 2026-08-31.
Other instructions, from other repositories
fieldtheory-cli CLAUDE.md
Instructions for afar1/fieldtheory-cli, covering claude.md, commands, architecture, key files and data flow.
siyuan AGENTS.md
AGENTS.md instructions for siyuan-note/siyuan, covering agents.md, 1. non-negotiable constraints, do not hand-edit, verification and prohibited operations and 2. project-specific rules.
chat-on-steroids AGENTS.md
Instructions for totec448-spec/chat-on-steroids, covering chat on steroids — the agent map, 1. the app in sixty seconds, 2. where the bugs actually are, name the identity, then find where it is lost and 3. what is authoritative.
AI-MarkDone copilot-instructions.md
Instructions for zhaoliangbin42/AI-MarkDone, covering ai copy enhance - ai coding agent instructions, project overview, architecture patterns, adapter pattern for multi-platform support and shadow dom isolation.
chat-on-steroids CLAUDE.md
Instructions for totec448-spec/chat-on-steroids: Read and follow AGENTS.md before changing this repository.
AI-MarkDone AGENTS.md
Instructions for zhaoliangbin42/AI-MarkDone, covering ai-markdone engineering guide, project facts, read order, common commands and non-negotiables.