majia-guanyuan: Instructions file for Codex

AGENTS.md

majia-guanyuan AGENTS.md is an instructions file for Codex, OpenCode from maojiebc/majia-guanyuan. It costs 2,002 tokens per session, scanned A, original, MIT.

A project instruction file for working with Guandata BI, a business-intelligence platform for analyzing and managing data. It explains the required reading order, available tools, and how this project builds on Guandata's official skill family.

In plain words
What is it for?
Use it when querying Guandata BI, working with dashboards or datasets, running data preparation tasks, or extending this project's additional capabilities.
Why use it?
It keeps agents within the project's operating rules and directs standard queries, cards, ETL, and dataset work to the appropriate official tools.

Instructions file for CodexOpenCode

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

This is maojiebc/majia-guanyuan's own configuration. It tells Codex and OpenCode how to work on majia-guanyuan 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 majia-guanyuan configures →

Reuse

Borrowing it

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

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 majia-guanyuan AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/maojiebc/majia-guanyuan/agents-md"><img src="https://agentmods.dev/badge/instructions/maojiebc/majia-guanyuan/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,002 This file is loaded in full into every session.
When invoked 2,002 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 $0.02002 $0.02002
Opus 5 $0.01001 $0.01001
Sonnet 5 $0.00400 $0.00400
Haiku 4.5 $0.00200 $0.00200

Measured 10d ago against content hash d78b7aab4b59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

majia-guanyuan 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 · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — majia-guanyuan

This file is read by:

  • OpenAI Codex as project-level instructions (when cwd is inside this repo)
  • Hermes / gbrain as a resolver file (alternative to RESOLVER.md)
  • Other AGENTS.md-aware tools (e.g., Cursor, Aider)

What this repo is

A Claude Code Skill for Guandata BI (观远 BI) — a tool-agnostic agent skill packaged so it works with Claude Code, OpenClaw, Hermes/gbrain, Codex, and any other agent that recognizes SKILL.md frontmatter.

V3.0.0 重定位 — 「马甲实战版」: after the official Guandata BI skill family went public on 2026-06-03 (@guandata/guanskill: guancli / guanvis / guanetl / guanwf / guands / guanmetric + per-skill AI skills; guanadmin / guanexport left the public family on 2026-06-04; guanmetric joined 2026-07-08, current family = 6), this skill was refactored ground-up from a self-built full-stack + fallback into a battle-tested gain-layer on top of the official family. The self-built HTTP client scripts/guandata.py (2789 lines) was retired and ~1600 lines of dead code removed. Standard query / card / ETL / dataset CRUD all route to the official family; this skill keeps only what the official DSL/commands can't reach.

Current structure — a router layer plus the hard-bone Parts:

  • 🧭 Router layer — standard query/card/ETL/dataset CRUD routed to the official family (guancli / guanvis / guanetl / guanwf / guands / guanmetric)
  • Part B — ETL governance, write, delete (incl. SmartETL full-chain rewrite methodology and ExecPlan workflow)
  • Part C — Custom chart HTML/CSS/JS injection & debugging on existing pages
  • Part C-12 — HTML application-style dashboard generation (descriptor patch linking selector → custom-chart dataView)
  • Part D — V7 Page/Card publish pipeline (draft/release state-machine bypass + node-level silent traps + mobile phoneLayout ZIP-inject)
  • Part E — SuperApp open-app development pipeline (reverse-engineering)
  • AI-native ADS design methodology — philosophy-layer doc (governance vs rebuild judgment)
  • Restaurant-chain BI formula playbook — 60+ SQL / RFM / Comp / DWD wide-table patterns

Read the full file on GitHub · 97 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 · 97 lines · 2,002 tokens per session scan A d78b7aab4b59

Subscribe to this mod's changes

majia-guanyuan AGENTS.md is an instructions file published in the GitHub repository maojiebc/majia-guanyuan (15 stars, last pushed 16d ago), licensed MIT. It adds 2,002 tokens to every session, about $0.0100 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.

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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