mcp_feedback_ji: Instructions file for Claude Code

CLAUDE.md

mcp_feedback_ji CLAUDE.md is an instructions file for Claude Code from olojiang/mcp_feedback_ji. It costs 1,305 tokens per session, scanned A, original, MIT.

Repository guidance for an enhanced MCP Feedback project, including its logs, troubleshooting steps, deployment process, and development conventions. MCP is a way for tools and applications to exchange structured requests and results.

In plain words
What is it for?
Use it when investigating feedback-panel, MCP server, or editor-hook issues, and when deploying or verifying changes to the project.
Why use it?
It gives developers a common way to diagnose problems by checking the right logs, confirming the running version, and following the project's deployment checks.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is olojiang/mcp_feedback_ji's own configuration. It tells Claude Code how to work on mcp_feedback_ji itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp_feedback_ji configures →

Reuse

Borrowing it

Nothing to install: this file belongs to olojiang/mcp_feedback_ji. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/olojiang/mcp_feedback_ji/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/olojiang/mcp_feedback_ji

Made for: Claude Code.

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.

agentmods badge for mcp_feedback_ji CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/olojiang/mcp_feedback_ji/claude-md/github.svg)](https://agentmods.dev/instructions/olojiang/mcp_feedback_ji/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/olojiang/mcp_feedback_ji/claude-md"><img src="https://agentmods.dev/badge/instructions/olojiang/mcp_feedback_ji/claude-md/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.

agentmods 80×15 button for mcp_feedback_ji CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/olojiang/mcp_feedback_ji/claude-md"><img src="https://agentmods.dev/badge/instructions/olojiang/mcp_feedback_ji/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,305 This file is loaded in full into every session.
When invoked 1,305 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01305 $0.01305
Opus 5.5 $0.00522 $0.00522
Sonnet 5.5 $0.00261 $0.00261
Haiku 4.5 $0.00130 $0.00130

Measured 2mo ago against content hash 1d5de7ea3e48, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp_feedback_ji CLAUDE.md 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 2mo 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.

CLAUDE.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Feedback Enhanced (Hunter Fork) — Project Guide

日志排查指南

日志文件位置

所有日志在 ~/.config/mcp-feedback-enhanced/logs/:

日志文件 说明 关键关键词
webview-YYYY-MM-DD.log (webview.log) 前端面板日志(webview JS → extension host 转写) drag, drop, browse-paths, addPathsToLru, savePathLru, showLruDropdown, at-search, connection_health, bootReport, resolveWebviewView
mcp-server-YYYY-MM-DD.log (mcp-server.log) MCP 服务端日志(stdio, feedback wait, progress) feedbackRequest, feedback_wait, progress_send, wait_lifecycle, request_billing_risk, Server started
hooks-YYYY-MM-DD.log (hooks.log) Cursor hooks 日志(duplicate wait deny, consume pending) action=deny_duplicate, action=skip_duplicate, consume_pending
session-journal.jsonl 会话生命周期结构化日志 session_displayed, session_updated, feedback_submitted

排查步骤

  1. 确认版本生效

    grep "resolveWebviewView" ~/.config/mcp-feedback-enhanced/logs/webview.log | tail -3
    

    看 v=2.5.1-ji.NNN 是否是刚部署的版本号。如果不是 → Reload Window (Cmd+Shift+P → Developer: Reload Window)。

  2. 确认脚本加载

    grep "bootReport" ~/.config/mcp-feedback-enhanced/logs/webview.log | tail -1
    

    scripts.errors 必须为空数组 "errors":[]。panelApp:true 等必须全 true。

  3. 前端交互问题(拖拽、按钮、@ 引用)

    grep -E "drag|drop|browse-paths|addPathsToLru|savePathLru|showLruDropdown|at-search" ~/.config/mcp-feedback-enhanced/logs/webview.log | tail -20
    
    • 拖拽不工作 → 找 dragenter@win / drop@win。如果没有 → Cursor webview 宿主层拦截了 DnD 事件,前端无法修复,用 📁 按钮替代。
    • LRU 不显示 → 找 addPathsToLru(确认在写入)和 showLruDropdown(确认 🕐 按钮点击生效)。如果只有 addPathsToLru 没有 showLruDropdown → 检查 var lruBtn 是否在 if (lruBtn) 之前声明(hoisting bug)。
    • @ 找不到目录 → 找 at-search query= 和 at-search dir_glob。如果没有 → extension host 未重载,需 Reload Window。
  4. MCP 服务端问题

    grep -E "feedbackRequest|wait_lifecycle|request_billing_risk|Server started" ~/.config/mcp-feedback-enhanced/logs/mcp-server.log | tail -20
    

Read the full file on GitHub · 82 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.

  1. 2mo ago First seen · 82 lines · 1,305 tokens per session scan A 1d5de7ea3e48

Subscribe to this mod's changes

mcp_feedback_ji CLAUDE.md is an instructions file published in the GitHub repository olojiang/mcp_feedback_ji (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,305 tokens to every session, about $0.0052 per session on Opus 5.5. 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 2026-08-31.

Related

mcp_feedback_ji CLAUDE.md compared with instructions from other repositories

mcp_feedback_ji CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp_feedback_ji CLAUDE.mdolojiang/mcp_feedback_jiInstructions file03mo agoMITA1,305Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot