pinkbin: Instructions file for Claude Code

CLAUDE.md

pinkbin CLAUDE.md is an instructions file for Claude Code from cccyd2003-qwq/pinkbin. It costs 1,397 tokens per session, scanned A, original, MIT.

A repository instruction file for Pinkbin, a desktop app that safely finds and removes application files such as caches and logs.

In plain words
What is it for?
Use it when adding or changing cleanup definitions, called scaffolds, and their Rust safety tests or desktop interface.
Why use it?
It records rules that prevent cleanup from deleting account data, chat databases, encrypted files, or other protected information.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code.

This is cccyd2003-qwq/pinkbin's own configuration. It tells Claude Code how to work on pinkbin itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pinkbin configures →

About the project

Pinkbin is an open-source disk analyzer and cleaner that shows storage usage, lets AI explain unfamiliar folders, and supports controlled deletion through cleanup scripts. It is for Windows users who want to understand and reclaim disk space while keeping deletions scoped and sending them to the recycle bin by default. The catalogue commands, instruction, and setting support agent-assisted use of Pinkbin.

cccyd2003-qwq/pinkbin · 1,361 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to cccyd2003-qwq/pinkbin. 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/cccyd2003-qwq/pinkbin/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/cccyd2003-qwq/pinkbin

Made for: Claude Code.

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.

agentmods badge for pinkbin CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cccyd2003-qwq/pinkbin/claude-md/github.svg)](https://agentmods.dev/instructions/cccyd2003-qwq/pinkbin/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cccyd2003-qwq/pinkbin/claude-md"><img src="https://agentmods.dev/badge/instructions/cccyd2003-qwq/pinkbin/claude-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.

agentmods 80×15 button for pinkbin CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cccyd2003-qwq/pinkbin/claude-md"><img src="https://agentmods.dev/badge/instructions/cccyd2003-qwq/pinkbin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,397 This file is loaded in full into every session.
When invoked 1,397 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01397 $0.01397
Opus 5 $0.00698 $0.00698
Sonnet 5 $0.00279 $0.00279
Haiku 4.5 $0.00140 $0.00140

Measured 9d ago against content hash d213ab238fd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pinkbin 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 9d 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.

CLAUDE.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pinkbin · 给 Claude 的工作约定

这份文件是仓库级硬约束,每次 Claude Code 会话会自动读。改 scaffold / 加 scaffold 时 Claude 必须按本文件 + .claude/commands/add-scaffold.md 走流程

项目背景

Pinkbin 是一个磁盘清理桌面 app(Tauri 2 + React + Rust)。核心是一组 scaffold TOMLscaffolds/<id>.toml)——每份描述一个常用软件的清理目标(缓存、日志、可选的历史媒体)和它的红线。Studio 面板按 scaffold 渲染卡片,用户可以按 scope 单独清理。

Hard rules(不可违反)

  1. Scope glob 红线:任何 [[scope]] 的 glob 不允许命中以下路径片段:

    • *.db*.db-wal*.db-shm(聊天/账号 DB)
    • **/db_storage/**(WeChat 4.x DB 群)
    • **/Msg/****/MultiMsg/**(WeChat 3.x 聊天数据)
    • **/Accounts/****/All Users/****/login/****/config/**(账号状态)
    • **/Favorite*/****/Fav/**(用户收藏)
    • **/key/****/crypto/**(加密物料)
    • 各家 IM 的"用户原始文件夹"(详见 docs/scaffold-requirements/<category>.md 的红线节)
  2. Safety test 强制:每份 scaffold 必须在 crates/scaffold/tests/<id>_safety.rs 落一个集成测试,包含正向断言(每个 scope 至少一条命中路径)+ 红线断言(一组红线路径必须 zero match)。模板见 crates/scaffold/tests/_templates/scaffold_safety.rs

  3. UI 防御三件套:任何调用破坏性 Tauri 命令(execute_plan / execute_scope)的前端组件必须满足:

    • <ErrorBoundary> 包裹(参考 apps/desktop/src/components/ErrorBoundary.tsx
    • 两步确认或 dry-run 预览,不允许直接 window.confirm(Tauri webview 行为不稳定)
    • 默认 mode = "recycle"(走系统回收站可恢复),delete 模式只在用户显式选择时使用
  4. 隐私:枚举用户数据目录时只用 Glob/ls 列文件夹名绝不 Read 聊天 DB / 媒体文件 / 账号 key 等用户内容。

Discovery loop(动手前的纪律)

写新 scaffold 或大改现有 scaffold 之前,先读这三个文件,理解当前状态

  1. crates/scaffold/src/lib.rs —— TOML schema、env 展开、detect 逻辑
  2. apps/desktop/src/components/Studio.tsx —— 当前 UI 怎么渲染 scope(看 expanded card 那一段)
  3. apps/desktop/src/types.tsScaffold / Scope 类型 —— 前后端 schema 镜像

漏掉这步的代价:你会按"想象中的 UI"设计 TOML,结果 UI 根本不渲染相关字段,回头返工。

实测回环(Phase 7 经验)

每次"真实路径勘测"完成后,必须回头修订需求文档——勘测往往会推翻 Phase 1-2 的假设。例如 WeChat 4.x 的 msg/ 目录在 3.x 是聊天 DB(红线),在 4.x 是用户接收的文件(L2 可清)。这种发现要写成需求文档的"实测附录"节,在写 TOML 之前完成。

Schema 一致性

Rust 的 Scaffold 结构体用 serde 做了 TOML ↔ JSON 双向序列化:

  • TOML 输入用 [[scope]](单数),通过 #[serde(rename(deserialize = "scope"))] 接收
  • JSON 输出给前端用 scopes(复数),通过 #[serde(rename(serialize = "scopes"))] 暴露

Read the full file on GitHub · 79 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. 9d ago First seen · 79 lines · 1,397 tokens per session scan A d213ab238fd5

Subscribe to this mod's changes

pinkbin CLAUDE.md is an instructions file published in the GitHub repository cccyd2003-qwq/pinkbin (1,361 stars, last pushed 1mo ago), licensed MIT. It adds 1,397 tokens to every session, about $0.0070 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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 · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens