Borrowing it
Nothing to install: this file belongs to shelizi/coding-tools-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shelizi/coding-tools-mcp/main/.agents/skills/mcp-probe-kit/SKILL.mdgit clone --depth 1 https://github.com/shelizi/coding-tools-mcpWrote 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/skills/shelizi/coding-tools-mcp/mcp-probe-kit)<a href="https://agentmods.dev/skills/shelizi/coding-tools-mcp/mcp-probe-kit"><img src="https://agentmods.dev/badge/skills/shelizi/coding-tools-mcp/mcp-probe-kit/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/skills/shelizi/coding-tools-mcp/mcp-probe-kit"><img src="https://agentmods.dev/badge/skills/shelizi/coding-tools-mcp/mcp-probe-kit.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 | $0.00083 | $0.01727 |
| Opus 5 | $0.00042 | $0.00864 |
| Sonnet 5 | $0.00017 | $0.00345 |
| Haiku 4.5 | $0.00008 | $0.00173 |
Grade A, and why
mcp-probe-kit 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP 调用时机 — mcp-probe-kit
本 Skill 只回答一件事：什么情况 → 调哪个 MCP。不是开发流程剧本。 由 mcp-probe-kit 自动安装；支持 MCP 的 Agent 客户端可从
.agents/skills/加载。
总规则
- 先查下表，有对应 MCP 就先调，再写代码 / 改文件
- 拿不准 →
workflow：{ "intent": "<用户原话>" } start_*会列出后续该调的 MCP；按返回逐步调用即可
意图速查（第一个该调的 MCP）
| 用户说什么 / 什么情况 | 第一个 MCP |
|---|---|
| 新功能、加模块、做需求 | start_feature |
| Bug、报错、异常、排查、不生效 | start_bugfix |
| 页面、组件、样式、UI、交互 | start_ui |
| 不熟代码、架构、调用链、影响面 | code_insight |
| 新项目上手、熟悉仓库 | start_onboard |
| 产品方案、PRD、原型 | start_product |
| 长周期自主迭代（Ralph） | start_ralph |
| 缺 AGENTS.md / 项目上下文 | init_project_context |
| 全新空仓库脚手架 | init_project |
| 写 commit message | gencommit |
| 代码评审、安全检查 | code_review |
| 重构、整理代码 | refactor（大改前先 code_insight） |
| 估算工时、排期 | estimate |
| 校验规格是否写全 | check_spec |
| 查历史踩坑、可复用经验 | search_memory |
| 需求不清楚、要澄清 | ask_user 或 interview |
| 工作报告、周报、git 汇总 | git_work_report |
| 不确定用哪个 MCP | workflow |
全工具：何时调用
编排入口 start_*（复杂任务的第一步）
| MCP | 何时调用 |
|---|---|
start_feature |
任何新功能 / 增强；会先搜记忆，再指引 add_feature → check_spec → 实现 |
start_bugfix |
任何 Bug / 报错；指引 fix_bug（真因）→ gentest → 测试 |
start_ui |
任何 UI / 页面 / 组件；指引设计系统、模板检索、实现约束 |
start_onboard |
新成员 / 新仓库快速建立心智模型 |
start_product |
从 0 做产品方案（PRD、原型思路） |
start_ralph |
需要多轮自主迭代、长任务循环时 |
路由
| MCP | 何时调用 |
|---|---|
workflow |
不确定该用哪个 MCP；或担心 Agent 跳过 MCP 直接写代码时 |
项目与规格
| MCP | 何时调用 |
|---|---|
init_project_context |
没有 AGENTS.md、docs/project-context/、图谱索引；大改前缺上下文 |
init_project |
空目录需要初始化项目结构 |
add_feature |
需要生成 docs/specs/<feature>/ 规格（通常由 start_feature 触发） |
check_spec |
规格写完后、写实现代码前；或 Bug 修完要过规格闸门 |
estimate |
需要故事点 / 工时 / 风险评估（通常在 add_feature 之后） |
代码分析（可直接调，不必等 start_*）
| MCP | 何时调用 |
|---|---|
code_insight |
读不懂代码、找入口、看调用链 / 影响面；大重构前；mode=impact 评估改动范围 |
fix_bug |
需要 TBP 真因分析指南（通常由 start_bugfix 触发） |
gentest |
需要补测试 / 回归用例（Bug 修复后、功能完成后） |
code_review |
用户要审查指定文件或 diff（含安全项） |
refactor |
需要分步重构计划；范围大时先 code_insight |
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 · 142 lines · 83 tokens per session scan A 2f793c28eaad
mcp-probe-kit is a skill published in the GitHub repository shelizi/coding-tools-mcp (0 stars, last pushed 16d ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,727 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…