What is naiyue-skills AGENTS.md?

Repository instructions for maintaining reusable agent skills across different coding hosts. They define where skills, shared rules, links, tests, and documentation should live.

Use them when adding or modifying skills, updating repository documentation, creating validation tests, maintaining symbolic links, or checking cross-host compatibility.

They prevent duplicated skill sources and inconsistent copies, while making changes easier to validate and keep compatible across hosts.

How tlzmw001/naiyue-skills configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to tlzmw001/naiyue-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/tlzmw001/naiyue-skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/tlzmw001/naiyue-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tlzmw001/naiyue-skills/agents-md/github.svg)](https://agentmods.dev/instructions/tlzmw001/naiyue-skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/tlzmw001/naiyue-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/tlzmw001/naiyue-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tlzmw001/naiyue-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/tlzmw001/naiyue-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,290 This file is loaded in full into every session.

When invoked 1,290 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	$0.01290	$0.01290
Opus 5	$0.00645	$0.00645
Sonnet 5	$0.00258	$0.00258
Haiku 4.5	$0.00129	$0.00129

Measured 12d ago against content hash a41a964bad5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

naiyue-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 12d 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 · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill 管理规范

单一源码

所有公开 skill 只在 skills/<skill-name>/ 维护。
.agents/skills/<skill-name> 和 .claude/skills/<skill-name> 只能是指向 skills/ 的符号链接，禁止放内容副本。
AGENTS.md 是仓库维护规则的唯一来源；CLAUDE.md 只导入本文件，不复制规则。
README.md 只维护 skill 清单、用途和安装说明；工作流细节写入对应 SKILL.md 或按需加载的 references/。

新增 Skill

先搜索 skills/，已有相近能力时优先扩展，不创建重名或职责重叠的 skill。
使用 naiyue-skill-builder 规划内容；当前宿主提供官方 skill-creator 时，用它初始化和追加校验。
目录名与 frontmatter name 必须一致，只使用小写字母、数字和连字符。
SKILL.md 只保留触发描述、主流程和资源导航；详细规则放 references/，确定性操作放 scripts/，输出素材放 assets/。
同时创建 .agents/skills/ 和 .claude/skills/ 入口，并在 README.md 登记。
新脚本必须有测试；没有脚本的 skill 至少通过结构校验和 L1/L2/L3 接线检查。

修改 Skill

修改前先读完整 SKILL.md 以及它明确要求的 reference，不凭 README 推断当前行为。
只改用户要求的能力，不顺便重构其他 skill，也不改变公开触发范围。
新增文件后同步更新 SKILL.md 导航、测试和校验；删除文件前确认没有引用和运行依赖。
assets/registry.yaml、assets/global-rules.md 等持久状态只能按对应反馈或模版流程修改；需要用户确认的规则固化不得自动执行。
使用反馈先落到测试、validator、schema 或脚本；只有无法机械检查的判断才写进提示词。

跨宿主兼容

公共 SKILL.md 使用 Agent Skills 通用结构，frontmatter 至少包含 name 和 description。
核心流程不得依赖 .agents/skills/、.claude/skills/、.codex/skills/ 或个人绝对路径。
执行随 skill 分发的脚本时，从当前 SKILL.md 所在目录解析；文档示例统一使用 SKILL_DIR。
agents/openai.yaml 只承载 Codex 展示信息，不能成为核心能力依赖。
宿主确有差异时，把差异限制在薄适配说明中，不复制整份 skill。

迁移 Skill

先检查源仓库状态，区分已跟踪源码、本机副本、草稿和运行产物。
多个宿主版本不一致时先做 diff，以已跟踪版本为基线，逐项吸收有价值的独有内容。
只迁运行必需文件；不迁 .env、本机设置、缓存、凭据、研究工作区和无关 skill。
迁入后消除宿主路径硬编码，建立两个入口并运行完整验证。
未经用户确认，不删除或改写原仓库。

不得提交

.env、API key、token、密码或带凭据的 URL。
.claude/settings.local.json、个人绝对路径和机器专用配置。
.DS_Store、__pycache__、.pytest_cache、*.pyc。
research/、sandbox、clones、临时报告和其他运行产物。
TODO、空函数、占位模板或没有接线的声明文件。

Git 发布边界

.gitignore 使用白名单模式：默认忽略所有顶层内容，只允许 skill 源码、双宿主入口、维护文档、测试和 CI。
skill 运行工作区统一放在仓库外、research/、runs/ 或 .runtime/；这些目录及其产物永不提交。
禁止用 git add -f 绕过忽略规则，也禁止为了提交一次运行结果而临时放宽 .gitignore。
新增顶层目录时默认不发布。只有确认它是可复用的 skill 源码、测试、文档或 CI 后，才允许修改白名单。
提交前检查暂存区和未跟踪文件；发现报告、原始响应、sandbox、clone、日志或凭据痕迹时先移出提交范围。

Read the full file on GitHub · 82 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.

12d ago First seen · 82 lines · 1,290 tokens per session scan A a41a964bad5b

Subscribe to this mod's changes

naiyue-skills AGENTS.md is an instructions file published in the GitHub repository tlzmw001/naiyue-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,290 tokens to every session, about $0.0064 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.

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

naiyue-skills: Instructions file for Codex