Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/redleaves/context-keepernpx agentmods add rules/redleaves/context-keeper/auto_verification_rulesWrote 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/rules/redleaves/context-keeper/auto_verification_rules)<a href="https://agentmods.dev/rules/redleaves/context-keeper/auto_verification_rules"><img src="https://agentmods.dev/badge/rules/redleaves/context-keeper/auto_verification_rules/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/redleaves/context-keeper/auto_verification_rules"><img src="https://agentmods.dev/badge/rules/redleaves/context-keeper/auto_verification_rules.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02497 | $0.02497 |
| Opus 5.5 | $0.00999 | $0.00999 |
| Sonnet 5.5 | $0.00499 | $0.00499 |
| Haiku 4.5 | $0.00250 | $0.00250 |
Grade A, and why
auto_verification_rules scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:8088/health How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧠 高效编程执行规则 - Context-Keeper
🎯 编程执行金字塔原则（执行编码之前一定要用户确认！！！）
🔧 执行编码
/ \
✅ 用户确认 🧪 完整验证
/ \
📋 详细设计 📊 质量保障
/ \
🤔 理清思路 🚀 高效迭代
/ \
🗂️ 业务逻辑链路
/
📈 依赖关系分析
正确的执行顺序：
📈 依赖关系分析 → 🗂️ 业务逻辑链路 → 🤔 理清思路 → 📋 详细设计
→ ✅ 用户确认 → 🔧 执行编码 → 🧪 完整验证 → 📊 质量保障 → 🚀 高效迭代
🌟 核心原则 - MANDATORY
-
🧠 思考先行 - THINK FIRST, CODE LATER
- 任何编码前必须完整理清思路
- 分析业务逻辑链路、依赖关系、层次脉络
- 一次性设计完整，避免反复修改删除
-
🤝 用户确认 - USER AUTHORIZATION REQUIRED
- 关键时机：详细设计完成后，执行编码前（必须！）
- 确认内容：技术方案、修改范围、风险评估、执行计划
- 沟通原则：用户反馈问题时先定位分析，达成一致得到用户授权后再编码
- 严禁行为：未经用户授权直接修改任何代码或配置
-
🎯 质量优先 - QUALITY & EFFICIENCY
- 完整验证流程确保代码质量
- 避免编译错误导致的冲动乱改
- 系统性思考，通篇考虑，精准修改
🔄 高效编程执行流程 - 5阶段法
🧩 阶段1：问题分析与思路梳理 - ANALYSIS PHASE
🔍 当用户提出问题/需求时，必须先完成：
-
问题定位分析
📌 具体问题是什么？ 📌 涉及哪些代码模块？ 📌 影响范围有多大？ 📌 根本原因是什么？ -
依赖关系梳理
🔗 上游依赖：哪些模块会影响当前问题？ 🔗 下游影响：修改会影响哪些功能？ 🔗 横向关联：同层级有哪些相关组件？ 🔗 配置依赖：需要哪些配置支持？ -
业务逻辑链路分析
➡️ 数据流向：从输入到输出的完整路径 ➡️ 调用链路：函数/服务间的调用关系 ➡️ 状态变化：系统状态如何流转 ➡️ 错误处理：异常情况的处理路径
📋 阶段2：详细设计方案 - DESIGN PHASE
🎨 输出完整的技术设计方案：
-
修改范围说明
📁 涉及文件：明确列出所有需要修改的文件 🔧 修改类型：新增/修改/删除/重构 ⏱️ 预估工作量：每个修改点的复杂度评估 -
技术实现方案
🏗️ 架构调整：如何调整现有架构 💡 算法逻辑：核心算法的详细描述 🔌 接口设计：API/接口的变更说明 📊 数据结构：数据模型的变化 -
风险评估
⚠️ 潜在风险：可能出现的问题 🛡️ 风险缓解：如何避免/处理风险 🔄 回滚方案：出现问题时的回退策略
✅ 阶段3：用户确认授权 - AUTHORIZATION PHASE
🤝 用户确认检查清单：
□ 问题分析是否准确？
□ 技术方案是否合理？
□ 修改范围是否可接受？
□ 是否有更好的替代方案？
□ 风险评估是否充分？
□ 是否授权开始编码？
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.
- 1mo ago First seen · 303 lines · 2,497 tokens per session scan A 58595d80ec4a
auto_verification_rules is a cursor rule published in the GitHub repository redleaves/context-keeper (155 stars, last pushed 9mo ago), licensed MIT. It adds 2,497 tokens to every session, about $0.0100 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
shared-plane-packages
Pattern for creating shared plane packages that serve both migration and runtime planes.