copilot-setting AGENTS.md

copilot-setting AGENTS.md is an instructions file for Codex, OpenCode from zexion7873/copilot-setting. It costs 2,786 tokens per session, scanned A, original, MIT.

A repository guide for AI coding agents working on a GitHub Copilot configuration project. It explains the project’s purpose, communication rules, architecture, validation commands, and where the authoritative style guidance lives.

In plain words
What is it for?
Guiding work on Copilot agents, skills, instructions, prompts, and hooks for Java 8, Maven, Spring Core 3.2, and Hibernate 4.2 projects.
Why use it?
It gives agents the repository-specific rules they need before changing configuration files that control other agents.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/zexion7873/copilot-setting/agents-md
Clone the repo
git clone --depth 1 https://github.com/zexion7873/copilot-setting

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 copilot-setting AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zexion7873/copilot-setting/agents-md.svg)](https://agentmods.dev/instructions/zexion7873/copilot-setting/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zexion7873/copilot-setting/agents-md"><img src="https://agentmods.dev/badge/instructions/zexion7873/copilot-setting/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,786 This file is loaded in full into every session.
When invoked 2,786 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.02786 $0.02786
Opus 5 $0.01393 $0.01393
Sonnet 5 $0.00557 $0.00557
Haiku 4.5 $0.00279 $0.00279

Measured 3d ago against content hash bf8c79c3697c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copilot-setting AGENTS.md scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`.github/hooks/scripts/block-dangerous-commands.sh` denies shell tool calls matching a blocklist (destructive `rm`/SQL/git, privilege escalation, `curl|sh`, and similar); the script and its regression suite (`bash .githu
AGENTS.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

copilot-setting — Agent Guide

Canonical guidance for any AI agent (Claude Code, OpenAI Codex, Cursor, GitHub Copilot, …) working in this repository. CLAUDE.md is a thin pointer that imports this file via @AGENTS.md, so every tool reads one source of truth; the authoritative format spec is .github/STYLE-GUIDE.md. Read both before editing. There are intentionally no per-directory AGENTS.md files — keep navigation in this single root file.

Communication Language

Always reply to the user in Traditional Chinese (繁體中文). File contents, code, identifiers, and commit messages remain in English per the conventions below — only the chat replies are in Chinese.

Repository Purpose

This repo is not application code — it is a configuration distribution for GitHub Copilot that defines a multi-agent system for Java 8 / Maven / Spring Core 3.2 + Hibernate 4.2 projects (no Spring Boot — declarative transactions via XML <tx:advice>). Everything under .github/ is content loaded by Copilot at runtime (agents, skills, instructions, prompts, hooks). When editing, you are editing prompt-engineering artifacts, not source code.

The target audience of the artifacts here is Copilot users working in downstream Java repos, not this repo itself. There is no build, no test suite, and no runtime — only Markdown content and one validation script.

Not part of the product (ignored state / dependencies / IDE config): .omc/, .omo/, .claude/, .codegraph/, .sisyphus/, .idea/, .vscode/.

Validation Commands

Run both before committing changes under .github/ (also enforced in CI via .github/workflows/validate-style-guide.yml):

bash .github/scripts/test-validate-style-guide.sh   # regression-test the validator itself
bash .github/scripts/validate-style-guide.sh        # validate the real tree

One-time local setup so the validator also runs on git commit (.githooks/pre-commit runs it against the staged index when .github/ markdown is staged):

Read the full file on GitHub · 144 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. 3d ago First seen · 144 lines · 2,786 tokens per session scan A bf8c79c3697c

Subscribe to this mod's changes

copilot-setting AGENTS.md is an instructions file published in the GitHub repository zexion7873/copilot-setting (1 stars, last pushed 1mo ago), licensed MIT. It adds 2,786 tokens to every session, about $0.0139 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.