r-summary-sop

A rule for turning a code change and its chat history into a documented development procedure. It asks for a file tree, a Mermaid dependency diagram, and notes about likely problems and fixes.

In plain words
What is it for?
Use it to document completed development work, show which files were added or changed, map their dependencies, and record implementation pitfalls.
Why use it?
It helps preserve how a feature was built, so future developers can understand the changes and repeat or maintain the work.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/xyzbit/ai-coding/r-summary-sop
Clone the repo
git clone --depth 1 https://github.com/xyzbit/AI-Coding
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 93 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00093
Opus 5 $0.00000 $0.00046
Sonnet 5 $0.00000 $0.00019
Haiku 4.5 $0.00000 $0.00009

Measured 2d ago against content hash 68959b3a6d48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

r-summary-sop 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.

cursor/rules/review/r-summary-sop.mdc · 13 lines

What it actually says

请结合此次代码修改 @Branch (Diff with Main Branch) 和聊天记录, 总结生成开发此功能的 sop, 文档结构参考如下:

## 1. 用树形结构展示新增|修改的文件

## 2. 文件依赖关系图 (Mermaid)

## 3. 注意事项(可能遇到的问题及解决方法)
Changes

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.

  1. 2d ago First seen · 13 lines · 0 tokens per session scan A 68959b3a6d48

Subscribe to this mod's changes

r-summary-sop is a cursor rule published in the GitHub repository xyzbit/AI-Coding (21 stars, last pushed 10mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 93 tokens. 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.