Borrowing it
Nothing to install: this file belongs to liyecom/liye-ai. 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/liyecom/liye-ai/main/CLAUDE.mdgit clone --depth 1 https://github.com/liyecom/liye-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/liyecom/liye-ai/claude-md)<a href="https://agentmods.dev/instructions/liyecom/liye-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/liyecom/liye-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 5.1 | $0.02156 | $0.02156 |
| Opus 5 | $0.01078 | $0.01078 |
| Sonnet 5 | $0.00431 | $0.00431 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
liye-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 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md (Kernel)
本文件是 liye_os（GitHub repo
liyecom/liye-ai）的启动路牌 + 最小常驻 context。 只放导航、命令、纪律；不放 SOP/协议/skill 全文。 本文件受机器门保护：guardrail ≤10,000 chars（node .claude/scripts/guardrail.mjs）； 改动本文件的 PR 标题须kernel:/governance:前缀或kernel-changelabel（Kernel Guard CI）。
System Role
- Layer: 0（制度底座）——LiYe Systems 的 governance / contract compiler + 窄控制面工具；语义入宪、实现下沉，不拥有预建通用 agent runtime。
- 系统级 SSOT:
_meta/portfolio/SYSTEMS.md（生态分层、BGHS 四分法、D0-D3 成熟度、依赖方向）。 - 项目级 SSOT:
_meta/contracts/。讨论生态角色/层级以 SYSTEMS.md 为准；讨论本仓治理以 contracts 为准。 - 本仓不做具体业务逻辑：向 domain engines（AGE/UGE/chaming）和按需执行体输出合约；常驻 runtime 必须重新满足 demand-pull 或 risk-pull。
治理面导航（2026-07 现状；计数会漂移，以命令重数为准）
| 资产 | 路径 | 一句话 |
|---|---|---|
| 契约 SSOT（22-schema gate） | _meta/contracts/ |
learning×13 · engine×2（v1+v2）· governance×3 · loop×1 · execution×1 · playbook×1 · proactive×1；其中 16 个注册在 validate-contracts.mjs schemaFiles[]，6 个由专用校验器覆盖 |
| loop contract v2（C1-C13） | _meta/contracts/loop/ |
governed work loop 契约语言层：schema + template + fixtures，两层校验（ajv 结构 + 语义派生）；v2 增 stop_condition/kill_switch/evidence_package/词表收紧；contract_status: schema_validated_only，背后无 runner |
| execution contract v0 | _meta/contracts/execution/ |
受治理执行的 schema + template + fixtures：approval/resume/receipt/readback/verdict/rollback-ref；contract_status: schema_validated_only，不隐含 runner/runtime |
| 政策 | _meta/policies/ |
DEFAULT_SKILL_POLICY.md（9 条，Policy 9=Surgical Scope）+ BACKLOG_INTAKE_POLICY.md（agent 只 propose、operator 翻牌） |
| ADR | _meta/adr/ |
22 份；新决策先查重再增 |
| SPEC | _meta/specs/ |
跨仓 SPEC（含 user-growth-engine） |
| 学习管线 | .claude/scripts/learning/ |
import_facts → pattern_detector → crystallizer → promotion → heartbeat → metrics → phase4_entry_gate；全部 operator/CI 触发，无调度器 |
| 学习源注册表 | .claude/config/learning_sources.yaml |
写门之一：enabled + expected_manifest_hash 双字段；arm 只授权 import 信任，不授权 emit/平台写 |
| 外源引入 | tools/source-intake/ |
URL→artifact 受控轨道 S0-S6 七阶三门；tools/github-scout/ 只读探查 |
| skill 工厂 | _meta/skill-factory/ |
SFC v0.2 契约 + 单一 SSOT frontmatter 解析器 + sfc-ci.yml |
| 台账 | _meta/contracts/ledger/ |
manifest reality 每日 append-only 记录（Band B 时钟证据） |
| 改革蓝图 | _meta/reform/ |
v1.1 |
| Portfolio disposition evidence | _meta/portfolio/decommission/ |
主轴 B 与 websites 的 inventory；只记录证据/目标处置，不授权迁移、关停或逐仓定级 |
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 · 81 lines · 2,156 tokens per session scan A 3b7a1a151397
liye-ai CLAUDE.md is an instructions file published in the GitHub repository liyecom/liye-ai (33 stars, last pushed today), licensed Apache-2.0. It adds 2,156 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 2026-08-30.
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.