What is project-blueprint AGENTS.md?

Project instructions for an open-source Markdown package that helps create development standards, documentation, delivery pipelines, testing rules, and Git conventions for new projects. It includes a seven-step workflow and a library of reference material.

Use them when updating the blueprint, checking its installation and documentation, or maintaining its GitHub and Gitee release workflow.

They give an AI coding assistant a defined project identity and working procedure when the repository itself has no program to build or test.

How shuguang1994/project-blueprint configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to shuguang1994/project-blueprint. 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/shuguang1994/project-blueprint/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/shuguang1994/project-blueprint

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/shuguang1994/project-blueprint/agents-md/github.svg)](https://agentmods.dev/instructions/shuguang1994/project-blueprint/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/shuguang1994/project-blueprint/agents-md"><img src="https://agentmods.dev/badge/instructions/shuguang1994/project-blueprint/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/shuguang1994/project-blueprint/agents-md"><img src="https://agentmods.dev/badge/instructions/shuguang1994/project-blueprint/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,292 This file is loaded in full into every session.

When invoked 5,292 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	$0.05292	$0.05292
Opus 5.5	$0.02117	$0.02117
Sonnet 5.5	$0.01058	$0.01058
Haiku 4.5	$0.00529	$0.00529

Measured 15d ago against content hash cb0d065bc064, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project-blueprint 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 15d 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 · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Blueprint 项目开发规范 (AGENTS.md)

AI 编程助手的强制开发规范。v2.0.0 | 更新: 2026-10-14（建立 2026-08-01） AI 工具: Trae | 加载: always_applied

一、项目身份

项目: Project Blueprint — 为新项目一键建立完整 AI 编程规范体系（AGENTS.md + 文档骨架 + CI/CD + 测试制度 + Git 规范）的开源 AI Agent 技能包。
形态: 纯 Markdown 项目，无代码、无构建、无测试、无运行依赖。核心逻辑为 SKILL.md（113 行索引层 + references/step-*.md 7 个 Step 细节），配套 references/ 知识库与 scripts/ 门禁层。
技术栈: Markdown (SKILL.md 格式) + 95 组件条目知识库（18 个二级章节 / 16 个技术栈维度） + MCP 工具知识库 + 门禁配方库 + 宪法层生长机制 + WebSearch 联网回退
版本: v2.0.0（语义化版本，tag 发布）
仓库: GitHub origin = https://github.com/shuguang1994/project-blueprint / Gitee gitee = https://gitee.com/shuguang1994/project-blueprint
作者: 曙光 (shuguang1994) | License: MIT
安装: npx skills add shuguang1994/project-blueprint（国际）/ npx skills add https://gitee.com/shuguang1994/project-blueprint.git（国内）/ dsh plugin --profile web add 'github:shuguang1994/project-blueprint'（DeepSeek Harness）

二、常用命令

# 本仓库无编译/测试命令，常用操作为 Git 双远程推送：
git add <files>                                # 暂存（按文件逐一添加，勿 git add -A）
git commit -m "<type>(<scope>): <description>" # 提交
git push origin main                           # 推送 GitHub
git push gitee main --tags                     # 推送 Gitee 镜像 + 版本标签
git fetch origin && git fetch gitee            # 同步双远程
git revert <commit>                            # 线上问题回滚

# 本仓库门禁层（scripts/）实跑：
npm run verify                                 # 统一入口（= node scripts/verify.mjs）
npm run verify:ci                              # 全量（= --stage=ci，CI 用同一入口）
node scripts/verify.mjs --stage=pre-push       # 按阶段过滤
node scripts/check-constitution.mjs            # 宪法自校验（AGENTS.md 红线 ↔ 门禁清单）

# 门禁装配点（见 4.6）：
#   CI      → .github/workflows/verify.yml（push / PR 自动跑 --stage=ci）✅ 已装配
#   pre-push → 未装配（单行启用：git config core.hooksPath .githooks，见 4.6）⚠️

# 技能安装/更新（验证对外文档描述一致性时参考）：
npx skills update project-blueprint

# DSH 插件包同步（修改根 SKILL.md / references/ 后，发版前运行）：
node dsh-plugin/scripts/sync-skill.mjs

Read the full file on GitHub · 228 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.

15d ago Changed · +2 lines · +197 tokens per session cb0d065bc064
1mo ago Changed · +15 lines · +590 tokens per session 6eec9e9833d0
1mo ago Changed · +33 lines · +1,316 tokens per session e8d10e271d35
1mo ago First seen · 178 lines · 3,189 tokens per session scan A 323cd13b1051

Subscribe to this mod's changes

project-blueprint AGENTS.md is an instructions file published in the GitHub repository shuguang1994/project-blueprint (23 stars, last pushed 15d ago), licensed MIT. It adds 5,292 tokens to every session, about $0.0212 per session on Opus 5.5. 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.

Claude Code agent-skills ai-coding deepseek-harness dsh dsh-plugin

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 · 9,715 tokens

project-blueprint: Instructions file for Codex

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Project Blueprint 项目开发规范 (AGENTS.md)

一、项目身份

二、常用命令

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

vscode model-prompts.instructions.md