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.
npx skills add ALLezSung/MCP-Control --skill pinming-formwork-checkgit clone --depth 1 https://github.com/ALLezSung/MCP-ControlWrote 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/allezsung/mcp-control/pinming-formwork-check)<a href="https://agentmods.dev/skills/allezsung/mcp-control/pinming-formwork-check"><img src="https://agentmods.dev/badge/skills/allezsung/mcp-control/pinming-formwork-check/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/allezsung/mcp-control/pinming-formwork-check"><img src="https://agentmods.dev/badge/skills/allezsung/mcp-control/pinming-formwork-check.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 | $0.00096 | $0.02518 |
| Opus 5 | $0.00048 | $0.01259 |
| Sonnet 5 | $0.00019 | $0.00504 |
| Haiku 4.5 | $0.00010 | $0.00252 |
Grade A, and why
pinming-formwork-check 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 10d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
品茗模板工程快速验算与优化
操作已经打开的品茗工程。以当前模块、最新截图和软件本轮建议为事实来源;不要把一个模板类型的字段或通过值套用到另一类型。
总体策略:先规划,再连续执行
- 首次调用
get_active_window后建立本轮状态表:模块/页签、窗口位置和尺寸、已确认的控件坐标、失败对象、建议原文、旧值和待改值。先读取 references/ui-coordinate-map.json;布局与坐标表匹配时不为初始化额外调用全屏get_screenshot。 - 每次工具调用前先完成下一段动作的规划;不要“调用一个 MCP 工具、重新分析、再调用下一个”。同一页面上的连续动作应一次规划完。
- 不做无信息增益的调用:不要反复调用
get_screen_size、get_cursor_position、剪贴板读取或全屏截图。已验证页面优先复用坐标表,不为每次点击重新读光标。 - 默认每轮只在两种情况下截图:读取验算结果文字,或完成本轮全部编辑后做一次整体复核。取消逐字段截图确认和逐字段截图复核。
首次准备(只做一次)
- 调用
get_active_window。标题不是“品茗建筑施工云安全计算软件”时,调用focus_window(优先不带模块后缀的主标题),再调用一次get_active_window;确认正确后不要重复聚焦。 - 确认品茗与 MCPControl 权限相同。品茗通常以 High(管理员)运行;不要另起低权限 MCPControl 服务。
- 只做一次鼠标注入探测:
move_mouse到安全空白位置,等待 200–300 ms,再调用get_cursor_position。位置未变化就停止并要求以管理员模式重启 Codex/MCPControl。后续仅在窗口移动、缩放、焦点异常或工具报错时复测。 - 读取 references/ui-coordinate-map.json,用活动窗口位置和尺寸把客户区坐标换算为屏幕坐标。若标题、模块、窗口尺寸和页面均匹配已验证布局,直接使用缓存坐标;只有模块/页面未知、布局不匹配或需要读取当前值时才截取局部/整体截图。
- 除非窗口坐标与坐标表明显不一致,不调用
get_screen_size。坐标表存储的是客户区相对坐标,不是屏幕坐标;按坐标表中的窗口偏移和缩放公式换算。
MCPControl 操作规则
- 已验证页面的快速模式为:从坐标表换算屏幕坐标,
move_mouse → click_mouse。不为每次点击调用get_cursor_position;仅在首次校准、窗口变化或动作异常时调用。 - 默认 keysender 的鼠标动作可能异步返回;普通控件只等待 300–500 ms 后继续。若下一步是键盘输入,等待 500 ms;若下一步是普通导航,等待 300 ms。
- 不使用带坐标的
double_click(x, y)。click_at在默认 keysender 后端中可能在移动完成前返回;除非已确认使用同步的 AutoHotkey 后端,否则不要依赖它做关键点击。 - 不把工具返回的“成功”当作动作已完成。输入和点击后按上面的短等待继续,不用空调用等待;在本轮全部编辑完成后用一次整体截图校验。
- 快速计算后先调用
get_active_window,不先做全屏截图:若标题包含“快速计算”,直接截取结果窗口区域读取文字;若仍是主窗口,等待 1 秒后再读一次活动窗口,必要时才截图确认。 - 关闭结果窗口统一使用
press_key_combination({keys:["alt","f4"]});escape可能无效。布局未变时直接使用缓存坐标编辑,不要为了重新定位立即截图。 - 不使用剪贴板读取来判断焦点。默认不调用任何剪贴板工具;只有长文本输入确有必要时才使用剪贴板粘贴。
- 坐标表只提供候选点。首次使用某模块或页面时,用一次局部截图确认标签、单位和字段值;确认后在本轮缓存坐标。窗口移动、缩放、滚动、切换页签或出现模态窗口后立即使缓存失效。
- 右侧参数页签和左侧荷载子页签优先使用坐标表中标记为
confidence: high且已截图验证的点;“新浇混凝土板工程属性”“支撑体系设计”“荷载设计”是区域锚点,不是可点击按钮。切页后只用截图确认激活页签,不修改参数。
快速计算循环
默认最多 10 轮;每轮按以下顺序执行:
- 在当前已验证编辑页,使用坐标表中的“快速计算”缓存坐标触发左侧按钮;不要重复截图找按钮。
- 点击后先等待约 3–4 秒调用
get_active_window。标题包含“快速计算”时,使用其返回的窗口位置和尺寸截取结果区域(grayscale: false);标题仍是主窗口时只再等待 1 秒并重读一次活动窗口。只有活动窗口状态不明确或需要读取文字时才调用截图。 - 绿色“快速验算通过”即成功:停止修改,保留结果窗口。红色“不通过”、不满足或超限即失败。一次性读取截图中的全部失败行,逐条记录模板部位、验算对象、失败模式、调整方向、完整参数名、单位和精确建议值。
- 失败时先判断能否批量修改:同一模块/页签、字段唯一、坐标表已验证、软件建议方向明确、同一轮不改变荷载/材料/截面/模型时,可在同一轮合并最多 3 个互不冲突的字段,再只计算一次。若字段含义或坐标不确定,拆分处理。
- 用一次
alt+f4关闭结果窗口,使用缓存坐标集中编辑所有本轮字段;不逐字段截图。字段输入完成后等待 300–500 ms。 - 在再次点击“快速计算”之前,截取一次包含所有修改字段的整体编辑区,统一确认标签、单位、方向和最终值。发现错误时只修正错误字段,再复核一次;确认无误后进入第 1 步。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 75 lines · 96 tokens per session scan A 230a81f3c63e
pinming-formwork-check is a skill published in the GitHub repository ALLezSung/MCP-Control (0 stars, last pushed 28d ago), licensed MIT. It adds 96 tokens to every session and 2,518 once invoked, about $0.0005 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…