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 rules/lawofall/agentcore/dev-processgit clone --depth 1 https://github.com/Lawofall/AgentCoreWhat 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 | $0.01004 | $0.01004 |
| Opus 5 | $0.00502 | $0.00502 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
dev-process 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.
What it actually says
开发工作流
项目采用「AI 全程开发、人做决策」模式，多 Agent 并行开发。
新会话冷启动
定位任务 → docs/索引.md「任务路由」；跑通 → docs/02-架构/本地开发.md；接缝 → seam-audit.mdc；桌面渲染自检 → frontend-preview.mdc；本地产品 AI / eval / probe → local-llm-dogfood.mdc（dev OpenCode Zen，禁默认踩 PLATFORM_API_KEY）；沉淀 → memory.mdc。产品介绍与仓地图 → AGENTS.md。
决策权限
| AI 自主决定 | AI 提案 → 人确认 | 人直接决定 |
|---|---|---|
| 实现细节、Bug 修复（不改契约）、测试/重构 | 架构选型、新依赖、设计文档修改 | 功能范围、需求变更、发布决策 |
遇需人决策的节点，立即暂停并清晰描述问题和备选方案。
设计纪律
- 正向推导：用户需求 → 产品设计 → 技术实现；动手前答三问：谁用 / 解决什么真实问题 / 产品上如何呈现。为复用旧实现而裁剪需求 → 停。
- 证据按问题选（禁止「生产实测 > …」单一高低档；生产日志是个案观测，不是产品规格）：
| 在问什么 | 主证据 | 生产日志 |
|---|---|---|
| 产品该怎样 / 架构取舍 | 用户意图 + 设计文档 + 人确认 | 默认不打开 |
| 代码现在怎么跑 | HEAD + 单测 / conformance | 不打开 |
| 这次事故怎么发生的 | 用户点名的 cid/trace + HEAD | 只核这一次；没 ID 不 sync、不 --recent 猜 |
| 线上是否还有同类 | 仅用户明说巡检 / reviews | 存在性；禁占比/趋势外推 |
| 质量回归 | dogfood 金标 / eval | 不当金标 |
打开后禁止用一窗推断「通常如此」，禁止用日志压过 HEAD 或已确认设计。禁止编造观测值与生产 ID；用户对话正文不进仓，只留 ID + 脱敏摘述。查法 → conversation-logs.mdc。
补丁绊线
修复满足任一，先停、提根因重设计提案：1. 需新增兜底/对账/自愈/特例逻辑；2. 同一根因改 ≥2 层；3. 同一接缝第 3 次打补丁。拦截提案 → intercept-discipline.mdc。
开发准则
生产级代码（错误处理、类型、日志）；先 Protocol/ABC/Pydantic 再实现；共享类型放 shared/ 或 core/types/；核心逻辑有单测；委派 → multitask.mdc。
验证范围
三档定义见 AGENTS.md；窄化命令、门禁分段、反空转、真跑核证据 → verify-scope.mdc。
文件编辑安全
禁止用脚本批量改源码；用 StrReplace + replace_all 逐文件改；改完用 Read 自检。
并行开发 Git 约束
git status / git diff 不代表本会话改动：1. 用 Read 校验自己的改动；2. git 对不上是并行噪音，接受并继续；3. 禁止排查 git 内部；4. 仅用户明确要求才跑 git，非请勿 commit。
产品 AI 日志查询
未贴 ID、未明说查失败/巡检 → 不打开。用户给出 32 位 hex ID / UUID → 只读 conversation-logs.mdc 再动手（勿整篇读分析指南、勿为单次查询派探子），禁止在文件系统（含 agent-transcripts/）搜索这类 ID。
文档治理 → doc-governance.mdc。
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 · 62 lines · 1,004 tokens per session scan A 401a5c98e9d8
dev-process is a cursor rule published in the GitHub repository Lawofall/AgentCore (78 stars, last pushed 2d ago), licensed MIT. It adds 1,004 tokens to every session, about $0.0050 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 cursor rules, from other repositories
code-patterns
Python code style and recurring patterns (config, logging, errors, paths).
project-overview
Core project architecture, patterns, and conventions for the AI Documentation Generator.
cursorrules
You are an AI agent building the module: {{MODULENAME}} This module is part of the Mnemosyne Neural OS ecosystem by XPACEGEMS LLC.
backend-python
Python and FastAPI standards for the backend.
core-project-context
Canonical project context and ownership rules.
dashboard-typescript
React and TypeScript standards for the operator dashboard.