univer-sdk-skills: Instructions file for Codex

AGENTS.md

univer-sdk-skills AGENTS.md is an instructions file for Codex, OpenCode from dream-num/univer-sdk-skills. It costs 757 tokens per session, scanned A, original, Apache-2.0.

A guide for AI agents working on Univer, a toolkit for adding spreadsheets and related features to web or Node.js applications. It explains the project’s purpose, skill format, and writing rules.

In plain words
What is it for?
Use it when embedding Univer, adding enterprise features, running it on a Node.js backend, or developing custom plugins and skills.
Why use it?
It gives agents the project context and conventions they need to produce consistent, usable Univer-related help.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: reads ~/.codex or $CODEX_HOME, but also the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex.

This is dream-num/univer-sdk-skills's own configuration. It tells Codex and OpenCode how to work on univer-sdk-skills 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 univer-sdk-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dream-num/univer-sdk-skills. 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/dream-num/univer-sdk-skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/dream-num/univer-sdk-skills

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 univer-sdk-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dream-num/univer-sdk-skills/agents-md/github.svg)](https://agentmods.dev/instructions/dream-num/univer-sdk-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/dream-num/univer-sdk-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/dream-num/univer-sdk-skills/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 univer-sdk-skills AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dream-num/univer-sdk-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/dream-num/univer-sdk-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 757 This file is loaded in full into every session.
When invoked 757 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 $0.00757 $0.00757
Opus 5 $0.00378 $0.00378
Sonnet 5 $0.00151 $0.00151
Haiku 4.5 $0.00076 $0.00076

Measured 10d ago against content hash 499485d5fc2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

univer-sdk-skills 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 10d 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 · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Univer Skills - Agent Guide

This file provides context for AI agents working on this skill project.

Project Purpose

This repository contains AI agent skills for the Univer project. These skills help AI agents assist developers with:

  1. Embedding Univer into existing web applications
  2. Integrating Univer Pro enterprise features (collaboration, import/export, printing, pivot tables, charts, shapes)
  3. Running Univer in Node.js backend environments for headless processing
  4. Developing custom plugins for Univer

Skill System Conventions

We follow the standard skill format:

skill-name/
├── SKILL.md           # Required. Frontmatter + instructions
├── agents/
│   └── openai.yaml    # UI metadata
├── references/        # Optional. Loaded on demand
├── assets/            # Optional. Templates, boilerplate
└── scripts/           # Optional. Executable utilities

Writing Rules

  1. SKILL.md body < 500 lines — split detailed content into references
  2. Frontmatter description is the trigger — include all "when to use" info there
  3. References are loaded on demand — always link them from SKILL.md with clear "when to read" guidance
  4. Code examples must be copy-paste ready — assume the agent will emit them directly
  5. Side-effect imports must be explicit — Univer's facade system requires import '@univerjs/xxx/facade'; never omit these

When to Update Skills

  • Univer releases a new major/minor version with breaking API changes
  • A new official package is added (update plugin-registry.md)
  • New facade methods are added (update facade-api-guide.md)
  • Community reports a skill led to incorrect code (fix the reference)

Testing Skills

After modifying skills, run validation:

# If your agent CLI provides a built-in validator (e.g. Codex):
python3 ~/.codex/skills/.system/skill-creator/scripts/quick_validate.py skills/univer-integrate
python3 ~/.codex/skills/.system/skill-creator/scripts/quick_validate.py skills/univer-plugin-dev
python3 ~/.codex/skills/.system/skill-creator/scripts/quick_validate.py skills/univer-pro-integrate
python3 ~/.codex/skills/.system/skill-creator/scripts/quick_validate.py skills/univer-node-backend

# Or use the standalone check script in this repo:
python3 scripts/validate.py skills/univer-integrate
python3 scripts/validate.py skills/univer-plugin-dev
python3 scripts/validate.py skills/univer-pro-integrate
python3 scripts/validate.py skills/univer-node-backend

Read the full file on GitHub · 80 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. 10d ago First seen · 80 lines · 757 tokens per session scan A 499485d5fc2a

Subscribe to this mod's changes

univer-sdk-skills AGENTS.md is an instructions file published in the GitHub repository dream-num/univer-sdk-skills (9 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 757 tokens to every session, about $0.0038 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens