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/lzzlhy/archview/agents-mdgit clone --depth 1 https://github.com/LZZLHY/archviewWrote 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/lzzlhy/archview/agents-md)<a href="https://agentmods.dev/instructions/lzzlhy/archview/agents-md"><img src="https://agentmods.dev/badge/instructions/lzzlhy/archview/agents-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 | $0.01400 | $0.01400 |
| Opus 5 | $0.00700 | $0.00700 |
| Sonnet 5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
archview AGENTS.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 2d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
ArchView —— 给一个仓库画「模块之间怎么依赖」的架构图：拓扑全部来自 tree-sitter 静态分析（CodeGraph），
LLM 只负责给每个节点写一句人话摘要。同一份图通过 MCP 暴露给 IDE 里的 agent。单机、只绑 127.0.0.1。
这份文件只是路牌。按你被派来干的活挑一条：
| 你要干的事 | 去读 |
|---|---|
| 安装 / 使用 ArchView | SETUP-FOR-AI.md —— 从 URL 到看见图的完整剧本，含决策点与失败对策 |
| 改这个仓库的代码 | CONTRACT.md —— 硬约束地基，不是风格指南。四条铁律 + 冻结的节点 ID 方案 + 图 schema |
| 给某个工作区写语义摘要 | 那个工作区里的 <你的仓库>/.archview/AGENT-GUIDE.md，不是这里。它带着那个工作区的实况，每次重建自动刷新 |
| 了解设计取舍与已知限制 | README.md（第 3 节为什么值得存在、第 10 节谁不该用它） |
改代码之前必须知道的
铁律 1：LLM 永远不写拓扑。 节点、边、模块划分只能由 CodeGraph 的 tree-sitter 输出派生。
agent 只能提供 summary 与 tags。看到「模块总览少一条我确信存在的边」时，正确做法是接受它
（并去 README.md 第 10 节看解析边界），不是在 builder 里按包名猜补 —— 猜出来的拓扑就是
LLM 写拓扑的另一种形式。另外三条铁律（summary 非空 / layer 覆盖全部文件节点 / 文件级边必须上卷）
与它们的验收指标在 CONTRACT.md。
节点 ID 方案是冻结的：摘要文件用节点 ID 做 key，改 ID 等于作废所有人已有的摘要资产。
关键命令
pnpm install # 首次会刷一串 ENOENT WARN（bin 指向还不存在的 dist/），正常，别重试
pnpm build # 六个包：五个 tsc + packages/web 的 Vite
pnpm -r run typecheck # ⚠️ 必须在 build 之后，否则一定报 TS2307（跨包类型走 dist/*.d.ts，而 dist/ 是 gitignore 的）
验收（改完至少跑这几条；跑之前先清 ARCHVIEW_* 环境变量残留，否则你测的可能是另一个仓库）：
pnpm --filter @archview/server run test # 基线 16/16
node packages/server/scripts/acceptance.mjs # fixture 模式，基线 46 通过 / 0 失败
node packages/mcp/scripts/acceptance.mjs # fixture 模式，基线 37/37
node final-check.mjs # fixture 模式，基线 14/14 + 1 跳过（ArkTS 那项不适用）
node packages/core/scripts/selfcheck.mjs --workspace <工作区目录> # 9/9，**必须**是真实工作区
前三个不给 --workspace 就自建一次性 fixture 工作区（os.tmpdir() 下的 4 包小仓库，
自己的临时注册表，跑完删）——默认路径一个字节都不碰用户数据，陌生克隆什么都不用准备就能跑。
想打自己的真仓库再显式给 --workspace <id>：
node packages/server/scripts/acceptance.mjs --workspace <id> # 基线 47/0（ArkTS 工作区；只读，除非 --rebuild）
node packages/mcp/scripts/acceptance.mjs --workspace <id> # 它会**写**该工作区的 .archview/（有备份/还原护栏）
node final-check.mjs --workspace <id> # 基线 15/15（只读）
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.
- 2d ago First seen · 75 lines · 1,400 tokens per session scan A fa615c179617
archview AGENTS.md is an instructions file published in the GitHub repository LZZLHY/archview (0 stars, last pushed 10d ago), licensed MIT. It adds 1,400 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 2026-08-31.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.