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/williamchmw/bosscoding/agents-mdgit clone --depth 1 https://github.com/williamchmw/BossCodingWhat 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 | $0.01043 | $0.01043 |
| Opus 5 | $0.00522 | $0.00522 |
| Sonnet 5 | $0.00209 | $0.00209 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
BossCoding 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.
What it actually says
BossCoding 项目规则
给 AI 协作项目的开发流程地基:npx bosscoding init 一条命令装好规则文件、8 项守卫、CI 质检口、决策档案与技能,任何 coding agent 通吃。纯 Node ESM,运行时零第三方依赖。
包 https://www.npmjs.com/package/bosscoding | 仓库 https://github.com/KKKKhazix/BossCoding (公开,MIT)
线上是哪个版本跑 npm view bosscoding version 看——版本号是会变的状态,不写死在本文件里。
本文件是唯一的规则真身;CLAUDE.md 只是指过来的门牌,改规则只改本文件。
机器守卫:npm run preflight(单测+node bin/bosscoding.mjs check)。
导师模式
老板是产品经理,不是程序员。所有解释按下面写——这是硬规则,不许省略、不许「这次简单就从简」:
- 术语零假设:任何老板可能没听过的词,第一次出现就必须解释,哪怕之前的对话里解释过。
- 解释复杂方案先立一个贯穿全文的比喻,所有术语落进同一个比喻,中途不换。
- 每个方案必答四问:改什么 → 为什么现在这样是错的 → 改完什么效果 → 有什么风险。
- 数字换算成老板能判断的单位;汇报顺序:影响 → 结论与行动 → 需要老板决定的 → 技术细节。
- 结尾收敛成一个问题,明确写清「你只需要回哪一句」。
- 不贴大段代码、日志、堆栈;不用没展开过的英文缩写。
干活流程
- 一个任务一个 PR,默认 Draft;push 前跑
npm run preflight;禁止直推 main。 - 转 Ready 前确认没有别的 PR 在排队——并行干活,串行合并。
- CI 红了默认响应是撤销或修复,不是加新检查。
- 发版本:改
package.json版本号走 PR 合并,老板确认后gh workflow run publish.yml触发。走可信发布,不用令牌也不用验证码;本机npm publish只是应急退路。 - 合并不等于已发布:版本号进了 main 而没人触发 publish,npm 上就一直是旧版。发包是红线不能自动,所以改版本号的 PR 正文必须写明谁来触发;
npm view bosscoding version是唯一真实状态。
知识只有三个所在
| 想知道什么 | 去哪 |
|---|---|
| 机器允不允许这么写 | node bin/bosscoding.mjs check 与 node --test——规则真身是守卫和测试 |
| 当初为什么这么定 | docs/decisions/——只追加、不修改 |
| 现在实际什么状态 | 跑命令看真实输出,不要读文档猜 |
写作纪律:想往本文件加规则,先问三遍——能写成守卫吗?是一条裁决吗?是跑命令能看到的吗?三个都不是就别写。
红线(先说明并等老板确认,再动手)
- 发包(触发 publish workflow 或本机
npm publish)、仓库转公开、以老板名义对外发布任何内容——这三件是本项目的「上线」,一律先确认。 - 任何花钱的操作;动权限、密钥、账号设置。
- 密钥、token 永不进代码,只放
.env(守卫盯着)。 - 违反后伤到谁:框架的用户是拿它当地基的小白,一次坏发布会同时伤到所有装了它的项目——发布纪律比功能进度重要。
事故与立法(框架自身的立法纪律)
- 运行时零第三方依赖:筹备队必须在任意网络环境一条命令跑通,依赖树越深失败面越大。
npx boss update与任何更新机制永不改写用户的 AGENTS.md/CLAUDE.md——规则是老板的规则。- 新增守卫的前提:挂着一次真实事故,且误报经实测收敛。误报多的守卫会被用户关掉,比没有更糟。
- 模板与文案改动同样走 PR 与守卫;本仓库必须永远能被自己的
boss check检查通过(吃自己的狗粮)。
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.
- yesterday First seen · 52 lines · 1,043 tokens per session scan A 69b9a0c179e7
BossCoding AGENTS.md is an instructions file published in the GitHub repository williamchmw/BossCoding (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,043 tokens to every session, about $0.0052 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.
Other instructions, from other repositories
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.