Borrowing it
Nothing to install: this file belongs to onism1767-creator/potato. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/onism1767-creator/potato/main/CLAUDE.mdgit clone --depth 1 https://github.com/onism1767-creator/potatoWrote 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/onism1767-creator/potato/claude-md)<a href="https://agentmods.dev/instructions/onism1767-creator/potato/claude-md"><img src="https://agentmods.dev/badge/instructions/onism1767-creator/potato/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 5.1 | $0.04664 | $0.04664 |
| Opus 5 | $0.02332 | $0.02332 |
| Sonnet 5 | $0.00933 | $0.00933 |
| Haiku 4.5 | $0.00466 | $0.00466 |
Grade A, and why
potato 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 8d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — 给 Claude Code 的厂规(本仓库的最高行为约束)
这份文件是 Claude Code 在本仓库工作时每次会话都必须先读的规则书。它的目的只有一个:让 AI agent 在高速写代码时撞不穿架构边界,从而不把这个项目写成屎山。 规则分两类:🟥 红线(任何情况下不许越;越线即视为错误,必须停下来问人)和 🟧 约定(默认遵守,确有理由偏离要先说明)。 本文件的"项目定位 / 架构边界 / 数据契约 / 安全 / 可复现"几节是锁定的,与具体功能清单无关;只有 §11 的"第一版范围"会随产品决策更新。
0. 一句话项目定位(先理解再动手)
本项目是一个开源的 Claude Skill(SKILL.md)+ 命令行工具(CLI),用来测量一个品牌/网站在 Claude API(开启 web_search) 的回答中被**提及(mention)和被引用(citation)**的频率与结构。
它的本质是一个 可复现的代理测量框架(reproducible proxy measurement framework):
- 不是爬虫;是反复用一批冻结的问题去"问"AI,收集回答 + 引用 URL,再用确定性规则打分。
- 不是"AI 排名真相检测器";只测"Claude API web_search 这个表面在某配置下的表现"。
- 输出可追溯、可审计、带不确定区间的报告。
🟥 叙事红线(写注释、文案、报告、README 时都适用)
- 不许把本工具说成"测出了 Claude 曝光度真相 / AI 排名"。统一措辞:"Claude API web-search 可见度(代理测量)"。
- 报告/输出里凡涉及结论,必须可标注
surface_id与"本结果仅代表此引擎"。 - 行动层只给线索(leads),绝不生成"照做就能让 AI 提到你"的保证或建议清单。本工具是观测工具,不是 recommendation engine。
1. 架构层级与不可跨越的边界(🟥 核心红线)
数据严格分三类、单向流动,禁止回流、禁止跨层直读对方内部状态:
① 原始观测 (raw) ② 核验证据 (evidence) ③ 分析与行动 (analysis)
provider 原样返回 → 被引 URL 的核验/分类 → 指标/区间/gap/driver/报告
[只追加] [可重算] [完全派生]
核心流水线,每段职责单一、边界清晰:
probe → extract → verify → score → report
(I/O) (纯) (I/O) (纯) (渲染)
🟥 边界红线
- 只有
probe写原始层(raw store)。 原始层 append-only,任何其它模块不许覆盖、不许改写已写入的原始记录。 extract和score必须是纯函数:输入数据、输出数据;禁止网络请求、文件读写、读系统时钟、未播种的随机数。它们不许import任何网络/HTTP/SDK 库(见 §3)。- 只有
verify做被引页的抓取,结果写证据层;score只读证据层、不自己抓页面。 - 跨层只走契约对象(§2),不许一个模块 reach into 另一个模块的内部字典/私有属性。
- 一个文件 / 一个模块只做一件事。新逻辑不确定该放哪一层 → 停下来问人,不要"就近塞"。
2. 数据契约规则(🟥 单一真相源)
所有跨模块传递的数据形状,只在 src/aivis/contracts/ 里定义一次,用 pydantic(或 dataclass)带类型。包括但不限于:
RunManifest / RawResponse / Citation / BrandMention / EvidenceRecord / Metrics / FrozenConfig。
🟥 契约红线
- 禁止在
contracts/之外就近发明新的数据结构(不许在 pipeline 里临时造一个"差不多但不一样"的 dict 来传数据)。 - 需要新字段/新类型 → 先改
contracts/,再改用它的地方;改契约属于"会影响所有下游"的动作,必须先问人。 RunManifest必含字段(缺一不可,用于可追溯):provider / surface_id / model / tool_path / tool_version / locale / region / prompt_version / competitor_set_version / max_uses / budget_cap_usd / run_id / timestamp / search_count。- 冻结配置(
FrozenConfig)来自questions.yml+brands.yml,是显式传入的不可变对象,不许做成全局可变状态或环境隐式读取。任何配置改动 = 版本号 bump(新基线),不许静默混入既有趋势序列。
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.
- 8d ago First seen · 212 lines · 4,664 tokens per session scan A 198e826e0c37
potato CLAUDE.md is an instructions file published in the GitHub repository onism1767-creator/potato (168 stars, last pushed 2mo ago), licensed MIT. It adds 4,664 tokens to every session, about $0.0233 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.
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.
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.
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).
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).
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.
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.