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/wangjs-jacky/quick-ai/claude-mdgit clone --depth 1 https://github.com/wangjs-jacky/quick-aiWrote 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/wangjs-jacky/quick-ai/claude-md)<a href="https://agentmods.dev/instructions/wangjs-jacky/quick-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/wangjs-jacky/quick-ai/claude-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 | $0.01380 | $0.01380 |
| Opus 5 | $0.00690 | $0.00690 |
| Sonnet 5 | $0.00276 | $0.00276 |
| Haiku 4.5 | $0.00138 | $0.00138 |
Grade A, and why
quick-ai CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Quick AI 项目
VS Code 扩展项目,提供快速访问 Warp 终端、Claude CLI 和 Opencode CLI 的功能。
发布流程
发布前必须完成
-
更新 CHANGELOG.md
- 每次发布新版本前,必须更新 CHANGELOG.md
- 通过
git log --oneline查看自上次发布以来的提交记录 - 按照以下格式添加新版本的变更日志:
## [版本号] - YYYY-MM-DD ### Added / Changed / Fixed / Removed - 变更描述 -
版本号管理
- 在 package.json 中更新版本号
- CHANGELOG.md 中的版本号与 package.json 保持一致
- 在 CHANGELOG.md 底部添加版本对比链接
发布命令
# 1. 更新 package.json 版本号
# 2. 更新 CHANGELOG.md
# 3. 构建并发布
pnpm run deploy
OpenSpec 学习
以下内容用于学习 OpenSpec 理念。请 Claude 在协助时遵循渐进式引导原则。
项目背景
OpenSpec 是一种规范驱动的工作流方法,通过"先定义,后实现"的理念来提高软件开发的可预测性和质量。
核心理念
- Spec-Driven(规范驱动): 所有的变更都从编写规范开始
- Artifact Workflow(制品工作流): 通过一系列明确的制品(Proposal、Plan、Delta Spec 等)来推进变更
- Verification(验证): 实现完成后进行验证,确保与规范一致
项目结构
openspec/
├── config.yaml # OpenSpec 配置文件
├── specs/ # 主规范目录(存放系统级别的规范)
├── changes/ # 变更目录(存放进行中的变更)
│ └── archive/ # 已归档的变更
学习路径(渐进式)
第一阶段:理解概念(当前阶段)
你当前处于这个阶段,目标是理解 OpenSpec 的核心概念:
已了解的概念:
- ✅ OpenSpec 是规范驱动的工作流
- ✅ 项目使用
spec-drivenschema
下一步学习:
- 📝 理解 OpenSpec 的核心术语
- 📝 了解制品工作流的具体步骤
- 📝 掌握如何创建第一个变更
第二阶段:创建第一个变更
学习使用 OpenSpec 技能来创建和管理变更:
- 使用
/opsx:new或/opsx:explore开始探索 - 创建 Proposal(提案)
- 创建 Plan(计划)
- 创建 Delta Spec(增量规范)
第三阶段:实施与验证
- 使用
/opsx:apply实施变更 - 使用
/opsx:verify验证实现 - 使用
/opsx:archive归档完成的变更
第四阶段:高级用法
- 学习
/opsx:sync同步规范 - 批量归档变更
- 自定义配置和规则
给 Claude 的指令
引导原则
- 渐进式学习: 不要一次性灌输所有概念,根据用户当前的学习阶段提供适量的信息
- 实践优先: 鼓励用户通过实际操作来学习,而不是只阅读理论
- 提问确认: 在进行下一步之前,确认用户已经理解当前概念
- 提供示例: 使用具体的示例来说明抽象概念
交互模式
当用户提出问题时:
- 首先判断问题所属的学习阶段
- 提供适合该阶段深度的解释
- 询问是否需要更深入的说明或实践建议
当用户想要执行操作时:
- 简要说明将要执行的操作及其目的
- 执行操作后,解释结果和下一步选项
- 询问用户是否理解或有其他问题
OpenSpec 核心术语速查
| 术语 | 说明 |
|---|---|
| Change(变更) | 一个功能、修复或改进的完整工作单元 |
| Artifact(制品) | 变更过程中产生的文档,如 Proposal、Plan、Spec |
| Proposal(提案) | 描述"为什么"要做这个变更 |
| Plan(计划) | 描述"如何"实施这个变更的任务分解 |
| Delta Spec(增量规范) | 描述"做了什么"变更的详细规范 |
| Spec(规范) | 系统的完整规范文档 |
| Archive(归档) | 完成后保存变更记录 |
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 · 158 lines · 1,380 tokens per session scan A 603ed66bb06d
quick-ai CLAUDE.md is an instructions file published in the GitHub repository wangjs-jacky/quick-ai (5 stars, last pushed 5mo ago), licensed MIT. It adds 1,380 tokens to every session, about $0.0069 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
kilocode AGENTS.md
AGENTS.md instructions for Kilo-Org/kilocode, covering agents.md, build and dev, quality checks, products and package instructions.
agent-of-empires AGENTS.md
AGENTS.md instructions for agent-of-empires/agent-of-empires, covering repository guidelines, where to look, commands, code rules and tests.
awesome-vscode CLAUDE.md
Instructions for viatsko/awesome-vscode, covering claude.md, what this repo is, adding an entry, themes and linting / ci.
vscode-peacock AGENTS.md
AGENTS.md instructions for johnpapa/vscode-peacock, covering peacock — agent guide, project overview, repository structure, tech stack and build & run.
language-tools AGENTS.md
AGENTS.md instructions for prisma/language-tools, covering agent guide for prisma language tools, project overview, packages, documentation and quick start.
getspecstory copilot-instructions.md
Copilot instructions for specstoryai/getspecstory: Examine the file changes for the pull request.