vibe-coding-kit AGENTS.md

A governance and documentation rule set for the vibe-coding-kit project, written mainly in simplified Chinese. It defines project principles, naming rules, required documents, and where those documents must be stored.

In plain words
What is it for?
Use it when planning or building the project, writing product or development documents, recording progress, or deciding how files and code comments should be named and formatted.
Why use it?
It gives coding work a fixed structure and prevents unclear requirements, inconsistent file names, missing documents, and uncontrolled project complexity.

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/junliu1066/vibe-coding-kit/agents-md
Clone the repo
git clone --depth 1 https://github.com/Junliu1066/vibe-coding-kit

Made for: Codex, OpenCode.

Per session 2,663 This file is loaded in full into every session.
When invoked 2,663 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.02663 $0.02663
Opus 5 $0.01332 $0.01332
Sonnet 5 $0.00533 $0.00533
Haiku 4.5 $0.00266 $0.00266

Measured yesterday against content hash 3d0d280ec96b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibe-coding-kit 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vibe-coding-kit 治理宪法 (Governance Constitution)

这是 vibe-coding-kit 的最高治理文件。Codex 在每次对话开始时自动加载它。 在其他平台(ChatGPT、Codex)使用时,将本文件内容复制为 system prompt 前缀。 所有规则派生自 harness.json——那是唯一真实来源。


一、最高原则

  1. 复杂度是负债,不是资产。 每多一个组件、一个依赖,都是向未来借债。
  2. 需求没说清,等于没说。 AI 会朝着模糊的方向飞速跑偏。
  3. 先说问题,再说方案。 描述方案会锁死 AI,描述问题才有更优解。
  4. 没有代价的方案不存在。 不讲代价的推荐不可信。
  5. 维护成本是最终裁决。 一年后修不修得动,比什么都重要。

二、语言与格式

  • 正文:简体中文
  • 代码注释:简体中文
  • 变量名/函数名:英文,见名知意
  • 文件编码:UTF-8
  • 行尾:LF

三、文件命名强制规范

产出物 路径 模板
PRD 文档 docs/prd.md examples/PRD-模板.md
项目说明书 docs/项目说明书.md examples/项目说明书-模板.md
开发文档 docs/开发文档.md examples/开发文档-模板.md
进度账本 docs/进度账本.md examples/进度账本-模板.md
项目进度卡总表 .dsu/progress/index.md examples/项目进度卡-总表模板.md
模块进度卡 .dsu/progress/modules/duXX-xxx.md examples/项目进度卡-模块模板.md
任务 Closeout 卡 .dsu/progress/tasks/任务ID.md examples/项目进度卡-任务模板.md
  • 所有产出物写入 docs/ 目录。如 docs/ 不存在,先创建它。
  • 不得使用其他文件名或路径。
  • 项目进度卡是开发期上下文索引,固定写入 .dsu/progress/,不写入 docs/

四、必须产出的章节(不可跳过)

PRD(docs/prd.md)至少包含:

    1. 文档元信息(文档状态、版本、产品名称三项不可为空)
    1. 产品结论(含核心定位 + 明确不做)
    1. 用户、场景与形态(含"它活在哪"的明确决定)
    1. 验收标准(每条具体可验证,不能是"系统正常"这种空话)
    1. MVP 完成定义
    1. 以后再说

项目说明书(docs/项目说明书.md)至少包含:

  • 一句话
  • 需求基准描述
  • 产品思考模块(预留)
  • 选定技术栈
  • 验收清单
  • 以后再说清单
  • 决策复盘 / 案例库

开发文档(docs/开发文档.md)至少包含:

    1. 文档元信息(文档状态、版本、产品名称三项不可为空)
    1. 概述(含本期范围 + 本期不做)
    1. 总体架构
    1. 端到端流程
    1. 模块清单
    1. 目录结构
    1. 数据结构与存储
    1. 接口约定
    1. 核心算法 / 业务规则
    1. 分阶段里程碑
    1. 开发任务总表
    1. 测试计划
    1. 反馈回路

五、流程纪律(按门推进)★

派生自 harness.jsonworkflow 块。这是为了解决"AI 不按步骤推进、乱序跳步"而设的硬规矩。

  1. 以账本为状态来源。 docs/进度账本.md 是流程的唯一状态来源。每轮对话开场先读它,向用户报"当前在哪个阶段、第几步";不存在就照模板创建。
  2. 按门推进。 流程是 S1 需求 → S2 选型 → S3 上线 的有序流水线。每个阶段有出口门(exit_gate),每一步有退出条件。一步的退出条件没满足,不进下一步;上一阶段出口门没过,不进下一阶段。
  3. 每过一步回写账本。 做完一步立刻更新账本(标状态、推进当前步骤)。
  4. 跳步要留痕。 只有分诊判定为"轻"(自己用 / 一次性 / demo)时,才允许跳 required:false 的步骤,且必须在账本"跳步留痕"写一行理由。required:true 的步骤一律不准跳。
  5. 轻重两种模式。 轻模式可"几步合并、一次报门",但出口门无论轻重都要过——省的是停顿次数,不是产出质量。
  6. 红线优先。 涉及"动钱 / 动别人隐私"时,survival 的红线提示优先级高于"按门推进"——先停下来提醒找真人。
  7. 问题解决后沉淀案例。 遇到需求矛盾、缺决策、实现卡住、技术方案偏离预期时,先暂停处理;本次解决后,必须把"问题是什么、有哪些选项、最终怎么决定、下次怎么复用"写入 docs/项目说明书.md 的「决策复盘 / 案例库」。

Read the full file on GitHub · 162 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. yesterday First seen · 162 lines · 2,663 tokens per session scan A 3d0d280ec96b

Subscribe to this mod's changes

vibe-coding-kit AGENTS.md is an instructions file published in the GitHub repository Junliu1066/vibe-coding-kit (169 stars, last pushed 2mo ago), licensed MIT. It adds 2,663 tokens to every session, about $0.0133 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.