What is feedback-enhanced?

Rules for an interactive feedback system that lets users and an AI agent discuss complex development work in real time. It includes guidance for recording decisions, tracking progress and handling detailed inputs such as code and diagrams.

Use it to request feedback, clarify requirements, review architecture choices, confirm completed plans and keep a history of feedback sessions.

It gives unclear requirements and major technical choices a structured review process. It also keeps longer feedback sessions from losing their discussion history.

feedback-enhanced — Cursor rule for coding agents by Mr-chen-05: Rules for an interactive feedback system that lets users…

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/mr-chen-05/rules-2.1-optimized/feedback-enhanced

Clone the repo

git clone --depth 1 https://github.com/Mr-chen-05/rules-2.1-optimized

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/feedback-enhanced.svg)](https://agentmods.dev/rules/mr-chen-05/rules-2.1-optimized/feedback-enhanced)

Your own site

<a href="https://agentmods.dev/rules/mr-chen-05/rules-2.1-optimized/feedback-enhanced"><img src="https://agentmods.dev/badge/rules/mr-chen-05/rules-2.1-optimized/feedback-enhanced.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,968 This file is loaded in full into every session.

When invoked 2,968 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.02968	$0.02968
Opus 5	$0.01484	$0.01484
Sonnet 5	$0.00594	$0.00594
Haiku 4.5	$0.00297	$0.00297

Measured 4d ago against content hash 7c6606e1eb52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feedback-enhanced 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 4d 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.

project-rules/feedback-enhanced.mdc · 388 lines

How it starts

The opening of the file, as written. The whole thing — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🤖 Enhanced Feedback Mechanism - 增强反馈机制

专为复杂开发任务设计的智能反馈系统，支持1小时超时的深度交互。

🎯 核心原则

统一调用方法 - 只使用 mcp_mcp-feedback-enhanced_interactive_feedback 工具
简化触发机制 - 明确的触发条件，避免过度复杂化
用户体验优先 - 确保反馈界面能够正常启动和使用
持续迭代 - 根据反馈持续改进和优化

🚀 Commands - 命令

/feedback - 手动触发反馈
/feedback-config - 配置反馈设置
/feedback-history - 查看反馈历史
/feedback-summary - 生成工作摘要

用户语言触发命令

当用户使用以下自然语言时，自动调用 mcp_mcp-feedback-enhanced_interactive_feedback：

"调用反馈程序"
"打开反馈界面"
"启动反馈系统"
"开启反馈功能"

✨ Features - 功能特性

🕐 Extended Timeout - 扩展超时

1小时超时 - 充足时间进行复杂架构讨论
自动保存 - 防止长时间讨论中的数据丢失
断点续传 - 支持中断后继续讨论

📝 Rich Text Support - 富文本支持

代码片段 - 语法高亮的代码展示
架构图 - Mermaid图表支持
配置文件 - 格式化的配置展示
截图支持 - 图片和截图集成

🔄 Real-time Interaction - 实时交互

双向沟通 - AI与用户的实时对话
进度跟踪 - 任务进度实时更新
决策记录 - 重要决策自动记录

📋 Trigger Conditions - 触发条件

🔍 详细模式特殊规则

当用户设置了详细模式时，每次会话开始时自动调用反馈增强界面，确保用户对每个开发步骤都有充分的参与和确认。

自动触发场景

🔍 需求不明确

触发条件: 用户描述模糊或存在歧义示例: "帮我做个网站" (缺少具体需求) 反馈内容:

项目类型和规模
技术栈偏好
功能需求清单
时间和预算约束

🎯 重大决策

触发条件: 架构选择、技术栈选型等关键决策示例: 微服务 vs 单体架构选择 反馈内容:

项目规模和团队大小
性能和扩展性要求
运维能力和经验
长期维护考虑

✅ 方案完成

触发条件: 技术方案设计完成，需用户确认示例: 数据库设计方案完成 反馈内容:

表结构设计审查
索引策略确认
性能预期评估
扩展性考虑

🎉 执行完成

触发条件: 代码实现完成，需用户验收示例: API接口开发完成 反馈内容:

功能测试结果
性能指标达成
安全检查通过
文档完整性

🚨 错误发生

触发条件: 遇到无法自动解决的问题示例: 依赖冲突或环境问题 反馈内容:

错误详细信息
可能的解决方案
需要的用户操作
替代方案建议

🖥️ MCP Desktop Feedback Invocation - 桌面反馈程序调用

统一调用方法

唯一正确的调用方式: 使用 mcp_mcp-feedback-enhanced_interactive_feedback 工具

调用规范

工具名称: mcp_mcp-feedback-enhanced_interactive_feedback
必需参数:
- project_directory: 当前工作区路径
- summary: 当前状态与需要用户确认的要点
- timeout: 超时时间（推荐3600秒，即1小时）

标准调用示例

// 正确的调用方式
mcp_mcp-feedback-enhanced_interactive_feedback({
  project_directory: "e:\\AgentRules\\English\\rules-2.1-optimized",
  summary: "已启动 MCP 桌面反馈程序。请在窗口中填写意见或上传截图，提交后我将根据反馈继续迭代。",
  timeout: 3600
})

Read the full file on GitHub · 388 lines

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.

4d ago First seen · 388 lines · 2,968 tokens per session scan A 7c6606e1eb52

Subscribe to this mod's changes

feedback-enhanced is a cursor rule published in the GitHub repository Mr-chen-05/rules-2.1-optimized (172 stars, last pushed 10mo ago), licensed MIT. It adds 2,968 tokens to every session, about $0.0148 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.

Productivity Project management

feedback-enhanced