Borrowing it
Nothing to install: this file belongs to Principle-Labs/Corivo. 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/Principle-Labs/Corivo/main/CLAUDE.mdgit clone --depth 1 https://github.com/Principle-Labs/CorivoWrote 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/principle-labs/corivo/claude-md)<a href="https://agentmods.dev/instructions/principle-labs/corivo/claude-md"><img src="https://agentmods.dev/badge/instructions/principle-labs/corivo/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 | $0.02160 | $0.02160 |
| Opus 5 | $0.01080 | $0.01080 |
| Sonnet 5 | $0.00432 | $0.00432 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
Corivo 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
项目概述
Corivo 是一个融入用户已有工作流的赛博伙伴。它不是一个独立的 App,而是寄生在 Claude Code、Cursor、飞书等工具中的后台服务——自动从用户的 AI 对话和消息中采集信息,持续整理和更新,在合适的时机以 [corivo] 的名义主动提醒用户。
当前版本请以各 package 的 package.json 为准(workspace 内版本独立演进)
详细设计文档见 README.md
Package 文档
每个 package 内都有独立的 CLAUDE.md,包含该包详细的构建命令、目录结构、核心概念和开发规范:
packages/cli/CLAUDE.md— CLI 工具、数据库、心跳引擎packages/solver/CLAUDE.md— CRDT 同步服务器packages/plugins/claude-code/CLAUDE.md— Claude Code 插件
进入某个 package 工作时,优先阅读该 package 的 CLAUDE.md。
构建与测试(快速参考)
每个 package 独立管理,进入对应目录后操作:
# packages/cli
cd packages/cli
npm run build # tsdown
npm run dev # tsdown --watch
npm run test # vitest --run
npm run typecheck # tsc --noEmit
# packages/solver
cd packages/solver
npm run dev # tsx watch src/index.ts(开发热重载)
npm run build # tsc
npm run start # node dist/index.js
# packages/plugins/claude-code
cd packages/plugins/claude-code
# 配置/文档型 package,无独立构建步骤
测试(当前以 cli package 的 Vitest 套件最完整):
cd packages/cli
# 运行所有测试
npm run test
# 运行单个测试文件
npm run test -- __tests__/unit/database.test.ts
npm run test -- __tests__/integration/heartbeat.test.ts
npm run test -- __tests__/integration/claude-code-ingestor.test.ts
注意:
@corivo/cli是纯 ESM 模块。better-sqlite3是 CJS,通过createRequire(import.meta.url)加载。
包架构
packages/cli(@corivo/cli)
核心 CLI 工具,包含所有本地存储和智能处理逻辑。
数据流:
用户工具(Claude Code / Cursor)
│
▼
Ingestors / Cold Scan ← 采集原始信息
│
▼
CorivoDatabase ← better-sqlite3,存储于 ~/.corivo/corivo.db
│ (Blocks + Associations + Query Logs)
▼
Heartbeat Engine(每 5 秒)
├── processPendingBlocks → RuleEngine 标注(决策/事实/知识)
├── processVitalityDecay → 按标注类型衰减(决策最慢,知识最快)
├── processAssociations → 发现 Block 间关联(每 30s)
└── processConsolidation → 去重 + 摘要 + 补链(每 1min)
│
▼
CLI Commands(save / query / status / push / inject …)
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 · 241 lines · 2,160 tokens per session scan A e3e3d3bbf324
Corivo CLAUDE.md is an instructions file published in the GitHub repository Principle-Labs/Corivo (5 stars, last pushed 5mo ago), licensed MIT. It adds 2,160 tokens to every session, about $0.0108 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
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.