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/ling5477/cad-max/agents-mdgit clone --depth 1 https://github.com/ling5477/CAD-MAXWhat 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 | $0.01741 | $0.01741 |
| Opus 5 | $0.00870 | $0.00870 |
| Sonnet 5 | $0.00348 | $0.00348 |
| Haiku 4.5 | $0.00174 | $0.00174 |
Grade A, and why
CAD-MAX 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS(CAD-MAX 开发规范)
目的:让开发者与编程代理在 CAD-MAX 中遵循同一事实源、安全边界、模块边界、验证和 Git/CI 纪律。
1. 当前事实源
- 每轮任务先读取
docs/current/STATUS.md顶部的cad-max-current-authority机器可读区块。 STATUS.md是当前 Phase、下一动作和安全能力状态的唯一 authority。docs/current/ROADMAP.md只定义下一允许动作,不覆盖STATUS.md。README.md与docs/current/README.md只提供入口,不复制独立的阶段判定。docs/current/TESTING.md与docs/current/WORKLOG.md是 append-only evidence ledger,不参与当前阶段判定。docs/current/PHASE_1_AUTOCAD_CONNECTION_PLAN.md定义 Phase 1 work-batch 顺序,但不推进 Phase。scripts/docs/governance-workflow-contract.json是 authority schema、work-batch lifecycle、evidence 命名和 hard blocker 的机器合同;checker 必须读取它,不得复制状态列表。docs/current/evidence/phase-1/**保存不可覆盖 attempt evidence,不决定当前 Phase。- current 文档互相冲突时,停止写操作并报告
BLOCKED / CURRENT_AUTHORITY_CONFLICT。
2. 任务边界
开始前必须明确 repository、target files、excluded files、风险和验收标准,并执行:
Get-Location
git status --short
git branch --show-current
默认规则:
- 最小变更,不顺手重构、格式化或升级依赖。
- 不覆盖用户已有改动。
- review-only / audit-only 默认不修改文件。
- 任务开始时必须明确 target files、excluded files、docs budget、expected output 与 rollback boundary。
- 未执行的验证不得写成通过。
- 发现额外问题只记录;仅当其阻塞当前验收时做最小修复。
3. 模块边界
src/python/cad_max_mcp:MCP transport、配置、后端选择、客户端安全响应。contracts:语言无关 JSON Schema,不依赖 Python、.NET 或 Autodesk 类型。CadMax.Contracts:C# wire contract,必须与 JSON/Python camelCase 语义一致。CadMax.Bridge.Core:校验、注册、调度、超时、取消和结构化异常映射。CadMax.Bridge.Host:仅限 localhost 的开发/测试 Host。CadMax.AutoCAD.Plugin:未来 Autodesk Managed .NET API 边界;不得提交 Autodesk DLL。- Python 不得以 COM 绕过 C# Bridge 作为生产主路径。
4. 强制安全边界
- 默认保持
readOnly=true、allowWrite=false、allowScript=false、httpHost=127.0.0.1。 - Phase 0 不实现真实 AutoCAD 连接、DWG 读取或 DWG 修改。
- 未实现能力必须 fail closed,不能注册成功 stub 或伪造 drawing 数据。
- 不读取、提交或输出
.env、token、cookie、密钥、Autodesk 专有 DLL、SDK、许可证数据或完整本机路径。 - 外部 HTTP 必须有超时、错误映射和 loopback 限制;日志不得包含原始异常消息或响应体。
- 未来写操作必须另行通过权限、allowlist、document context、transaction、Undo、幂等和失败测试审查。
5. 文档纪律
- Code-first:普通代码任务默认不改文档;事实、入口或操作方式变化时才同步。
- Docs budget:
- 普通代码任务默认不改文档;确需记录时最多向
WORKLOG.md追加一条事实记录。 - 测试基线变化可追加
TESTING.md与WORKLOG.md。 - Phase 状态变化才允许修改
STATUS.md与 currentROADMAP.md。 README.md只在入口、架构、启动方式或阶段总状态变化时修改。- CI、安全、协议、Autodesk SDK、发布等高风险事项才新建专项计划。
- 普通代码任务默认不改文档;确需记录时最多向
- current 治理文档以中文为主;代码符号、命令、协议字段和状态 token 保留英文。
- ledger 只追加新证据,不重写历史失败;历史失败必须保留后续修复/重跑关联。
- 修改文档后必须运行
scripts/docs/verify-docs.ps1。
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 · 119 lines · 1,741 tokens per session scan A 1e1510e72d55
CAD-MAX AGENTS.md is an instructions file published in the GitHub repository ling5477/CAD-MAX (0 stars, last pushed 12d ago), licensed MIT. It adds 1,741 tokens to every session, about $0.0087 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.