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/kvker/ai-native-template/agents-mdgit clone --depth 1 https://github.com/kvker/ai-native-templateWrote 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.
[](https://agentmods.dev/instructions/kvker/ai-native-template/agents-md)<a href="https://agentmods.dev/instructions/kvker/ai-native-template/agents-md"><img src="https://agentmods.dev/badge/instructions/kvker/ai-native-template/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00926 | $0.00926 |
| Opus 5 | $0.00463 | $0.00463 |
| Sonnet 5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
ai-native-template AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
AI Native 上下文模板
这是一个通用的 AI Native 上下文模板，用于为任意类型的 AI 协作任务提供结构化上下文。
缩写说明：对话中出现的“AN”一般指 AI Native 的缩写。
模板定位
本模板不预设任务类型。它既可以承载代码开发，也可以承载文档写作、方案设计、数据分析、研究整理、内容创作、流程规划等任何需要多轮 AI 协作的任务。
核心目标：让 AI 在一致的上下文结构中理解目标、规范、背景和任务状态，减少重复沟通，提升协作质量。
模板结构
| 目录 | 用途 | AI 行为 |
|---|---|---|
| background | 稳定且可刷新的背景知识 | 任务默认只读，仅由初始化、刷新流程或用户明确要求更新 |
| conventions | 上下文约定规范、对话长期规则与优化记录 | 开始任务前按需读取；对话过程中自动感知并按需写入 |
| artifacts | 任务状态、上下文与检查证据 | 按任务需要读写；实际交付物只保存引用 |
| projects | 实际工作区 / 交付物根目录 | 按任务需要读取和写入，每个子目录为一个独立工作单元 |
| .agents/skills/an-init | 模板初始化技能，运行期技能暂存在其 assets/skills/ 中 |
模板阶段的入口技能；运行期技能以 SKILL.md.txt 暂存，模板阶段不可见；$an-init 完成后恢复文件名并移入 .agents/skills/，an-init 自身删除 |
projects/在本模板中被视为工作区根目录，子目录可以是代码工程、文档集、数据集、设计稿目录或任何需要被 AI 理解和操作的交付物集合。
约定
索引文件以路由和必要约束为主，不复制具体文档正文：[name](path/to/file)
AI 行为约束
- 禁止自行脑补未提及的需求、功能或业务逻辑。
- 所有背景知识必须来自实际材料或用户明确输入。
- 从工作区材料反推的信息要标注来源；无法确认的信息标记为“待确认”。
- 不主动读取或输出
.env、secrets/、credentials、密钥、token 等敏感文件；除非用户明确授权且任务必要。
必读规范
开始任务前按需读取以下规范：
| 规范 | 用途 |
|---|---|
| principles | AI Native 核心原则 |
| workflow | 标准工作流 |
| flow-policy | 流程轻重判断 |
| document | 文档编写规范 |
| rules | 对话过程中的长期记忆感知与沉淀 |
| memories | 对话优化记录索引 |
任务状态
活跃 Artifact 的唯一索引是 artifacts/index.json。根 AGENTS.md 不复制动态任务状态，避免任务执行修改高优先级指令文件。
每个 Artifact 的流程等级、生命周期状态和父任务 ID 记录在自身的 artifact.json；Review 结论记录在 review/review.json。字段契约见 workflow。
Skill 路由
当前处于模板阶段，唯一入口是 $an-init。支持 Slash Command 的客户端也可以使用 /an-init。
运行期 Skills 现在仅以 SKILL.md.txt 保存，不应提前路由或调用。初始化完成并重启客户端后，根 AGENTS.md 必须改为运行期 Skill 路由，并移除 an-init 入口。
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.
- 4d ago First seen · 60 lines · 926 tokens per session scan A 214fdbdf97d8
ai-native-template AGENTS.md is an instructions file published in the GitHub repository kvker/ai-native-template (101 stars, last pushed 23d ago), licensed MIT. It adds 926 tokens to every session, about $0.0046 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.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.