A conversation rule that requires an interactive feedback step during every exchange, with automatic reconnection after a timeout and a fallback after three real failures. The instructions are written in Chinese.

Use it to manage interactive confirmations, progress feedback, and long waits in workflows that provide the specified feedback tools.

It is intended to prevent an agent from ending a conversation without user interaction or losing the connection while waiting for feedback.

feedback — Skill for Claude Code and Codex by rooney2020

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.

Any agent

npx skills add rooney2020/qt-interactive-feedback-mcp --skill feedback

Clone the repo

git clone --depth 1 https://github.com/rooney2020/qt-interactive-feedback-mcp

Made for: Claude Code, Codex.

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/skills/rooney2020/qt-interactive-feedback-mcp/feedback.svg)](https://agentmods.dev/skills/rooney2020/qt-interactive-feedback-mcp/feedback)

Your own site

<a href="https://agentmods.dev/skills/rooney2020/qt-interactive-feedback-mcp/feedback"><img src="https://agentmods.dev/badge/skills/rooney2020/qt-interactive-feedback-mcp/feedback.svg" alt="Measured on agentmods" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,124 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00031	$0.02124
Opus 5	$0.00015	$0.01062
Sonnet 5	$0.00006	$0.00425
Haiku 4.5	$0.00003	$0.00212

Measured 8d ago against content hash f48eff27cf39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

feedback 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 8d 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.

examples/copilot/.copilot/skills/feedback/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

反馈交互规则

核心原则

每次对话都必须通过交互工具与用户保持持续沟通，禁止单方面结束对话。

工具选择策略

interactive_feedback 始终优先，不区分中间过程还是最终确认。只有连续失败 3 次后才降级到 AskQuestion。

场景	使用工具	说明
所有交互场景	interactive_feedback	始终优先使用
interactive_feedback 连续失败 3 次后	AskQuestion	降级备选

关键规则

所有交互（中间确认、方案选择、最终确认）都优先使用 interactive_feedback
只有 interactive_feedback 连续失败 3 次（非心跳的真正错误）后，才降级到 AskQuestion
降级后每次交互仍应先尝试 interactive_feedback，成功则恢复优先使用
用户说"等一下"/"稍后"/"我先离开"时，不要调用任何交互工具（避免超时浪费请求）

心跳保活机制

工作原理

interactive_feedback MCP 工具内置了 progress notification 心跳机制：

Qt 反馈窗口在等待用户输入时不会被关闭
工具在内部通过 MCP progress notification 保持连接，不会频繁返回心跳消息
工具会持续等待直到用户提交反馈或 timeout 到期（默认 12 小时）
只有在完整 timeout 到期后，才会返回心跳消息 [心跳]

心跳处理规则

正常情况无需处理心跳：工具会在内部保持等待，大多数情况下直接返回用户反馈
识别心跳：仅当 timeout 完全到期后，返回内容包含 [心跳] 关键词
静默重连：收到心跳后，不输出任何文字，直接再次调用 interactive_feedback（使用相同的 summary 和 project_directory 参数）
心跳不计入失败次数：心跳是正常行为，不算作失败

心跳流程

interactive_feedback(summary) → [内部 progress notification 保活] → 用户提交 → 返回反馈
                                                                  → timeout 到期 → [心跳] → 静默重新调用

超时重连机制

当 interactive_feedback 工具因 Cursor 侧超时或连接断开而失败时：

立即重新调用 interactive_feedback，使用相同的参数
不输出任何文字说明，直接静默重连
超时不计入连续失败次数
如果反复超时（连续 3 次），降级到 AskQuestion 并提供"重试 interactive_feedback"选项

Cursor MCP 工具注册表失效处理

长时间运行的 agent 会话中，Cursor 可能出现 MCP 工具注册表暂时失效，错误特征：Tool not found 或 Connection closed。

识别：错误信息包含 Tool not found 或 Connection closed
不计入失败次数：此类错误是 Cursor 暂时性问题
重试策略：首次 sleep 10s 后重试；之后每次 sleep 60s；最多重试 10 次
全部失败：降级到 AskQuestion，说明 Cursor MCP 连接异常及重试次数
重试成功后重置所有计数

tab_id 和 tab_title 参数规则

调用 interactive_feedback 时，必须传入 tab_id 和 tab_title 参数。

tab_id（会话唯一标识）

首次调用时必须随机生成一个全新的 UUID（使用 UUID v4 随机生成，严禁使用文档中的示例 UUID）
同一会话中所有调用必须使用相同的 tab_id
tab_id 用于去重：同一 tab_id 的新请求会自动替换旧 tab
不同会话必须使用不同的 tab_id
禁止直接复制文档示例中的 UUID，必须每次随机生成

Read the full file on GitHub · 162 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.

8d ago First seen · 162 lines · 31 tokens per session scan A f48eff27cf39

Subscribe to this mod's changes

feedback is a skill published in the GitHub repository rooney2020/qt-interactive-feedback-mcp (16 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 2,124 once invoked, about $0.0002 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.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens