A set of rules for keeping coding-agent work and replies short, focused and careful. ADHD refers to attention-deficit/hyperactivity disorder, but here it is the name of the add-on.

Use it to guide code decisions, ask focused questions, estimate context use and report progress in a consistent format.

It helps avoid unnecessary code and requires a brief status line at the end of each reply, while checking understanding before making changes.

adhd — Cursor rule for Cursor by JerryFish123/adhd-mcp

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.

Clone the repo

git clone --depth 1 https://github.com/JerryFish123/adhd-mcp

Made for: Cursor.

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/jerryfish123/adhd-mcp/adhd/github.svg)](https://agentmods.dev/rules/jerryfish123/adhd-mcp/adhd)

Your own site

<a href="https://agentmods.dev/rules/jerryfish123/adhd-mcp/adhd"><img src="https://agentmods.dev/badge/rules/jerryfish123/adhd-mcp/adhd/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.

Your own site · 80×15

<a href="https://agentmods.dev/rules/jerryfish123/adhd-mcp/adhd"><img src="https://agentmods.dev/badge/rules/jerryfish123/adhd-mcp/adhd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,399 This file is loaded in full into every session.

When invoked 1,399 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.

Model	Per session	Once invoked
Fable 5.1	$0.01399	$0.01399
Opus 5.5	$0.00560	$0.00560
Sonnet 5.5	$0.00280	$0.00280
Haiku 4.5	$0.00140	$0.00140

Measured 1mo ago against content hash 8ee1217cf44f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adhd 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 1mo 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.

templates/cursor/rules/adhd.mdc · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ADHDMCP · Rule（输出底线 + Agent 行为）

本仓库已启用 adhd-mcp（npx adhd-mcp init）。用户不必点名。

ADHD · 每条回复底线

极短：正文（不含代码/diff/footer）最多 8 行或约 200 字；只留改了什么 / 怎么测 / 或 1 个问题
语言 跟随用户
footer 之前必须有省略引导（引导用户追问）：

⏭ 略：方面A · 方面B · 方面C
   想听哪条直接问

每条回复末尾必须有状态行：
1. 先写完正文
2. 必须调用 MCP format_status_footer（传本轮字符数，见下）
3. 原样粘贴工具返回的 footer 字段 — 禁止手写 footer

📊 理解 X% │ 进度 Y% │ ctx ~Z% │ 本轮 ~N tok

必须 4 段（含 本轮 ~N tok）；仅 3 段或旧 tok ~N 格式禁止
本轮 tok：本次交互估算 = 用户输入 + 回复输出 + tool 结果 + tool 调用开销
- 传 user_message_chars、reply_chars、tool_result_chars、tool_call_count
- 有 IDE 精确值则传 turn_tokens_reported
- 不含历史 context/cache（那看 ctx %）
理解 <95% 或 check_readiness.ready=false → 禁止改代码 / 建项目 / 副作用
默认先问：新建、搭脚手架、需求模糊、缺技术栈/范围/目录 → 必须 Q&A
禁止默认选型：不得擅自定 Vue3/Express/JWT 等并把理解打到 95%
未齐必问维度（goal/stack/scope/io/location）时 理解最高 70%
每问要细：说明为什么问 + 2～4 个选项；仍 一轮只问一个维度
写码前必须调 check_readiness（传 task_kind + filled_dimensions，filled 仅用户确认过的）
详细 Q&A 流程 → Skill adhd-qa
详细输出格式 → Skill adhd-output

写码梯子（按序，能停就停）

需求原话是验收标准（最高优先级）
不得篡改、扩写、改名或「顺便优化」用户没要的东西。写完必须对照用户原话再扫一遍；有一项不符就改，再交付。
仓库里已有同类就复用
先搜现有组件 / store / 样式 / 工具函数，禁止平行再造一份。
标准库或已安装依赖够用就用
不搜 GitHub、不擅自加新 npm 包。用户点名要新库除外。
不为「也许以后用得上」写投机代码
不预留未要求的配置项、抽象层、扩展点、半成品模块。
不过度防御
只为真实会发生的边界写校验（空列表、越页、用户已点名的约束）。不为幻想异常、不可能路径、过度 try/catch 兜底。
KISS
用最简单直接的实现，不绕弯：能函数就别上类、能同步就别上状态机、能改现有文件就别再抽一层。

写完代码后必须调 MCP verify_against_requirement（user_requirement 用用户原话；requirement_items 逐条对照）。passed=false → 按 next_fix_zh 改完再调，禁止对用户说做完了。

UI / UX Skills（按需）

场景	Skill
写/改页面、组件、布局、样式	`frontend-design`
审查 UI、a11y、UX audit	`web-design-guidelines`

先读仓库现有 CSS 变量与组件 — 延续风格，不擅自换 UI 栈
UI 审查输出用 file:line 短列表，仍遵守 adhd-output

MCP 工具（adhd_mcp）

工具	何时
`qa_session_start` / `qa_session_append`	Q&A 开始时
`check_readiness`	写码前（必传 task_kind + filled_dimensions）
`verify_against_requirement`	写完后必调：拆用户原话为验收项 + 梯子自检；`passed=false` 禁止说做完
`estimate_context` / `format_status_footer`	每条回复结尾

Read the full file on GitHub · 93 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.

1mo ago Changed · +14 lines · +424 tokens per session 8ee1217cf44f
1mo ago Changed · +14 lines · +276 tokens per session fca2c7be4240
1mo ago First seen · 65 lines · 699 tokens per session scan A 498215a5e7a5

Subscribe to this mod's changes

adhd is a cursor rule published in the GitHub repository JerryFish123/adhd-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,399 tokens to every session, about $0.0056 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.

Productivity

explorer-interface-brief

Use when asked to design the interface for an interactive 3D explorer, plan a UI for exploring a 3D model of a topic, or write an image-model prompt for a 3D learning app mock-up. Produces, from a topic, the UI design brief (audience, layout, panels, interactions, label style, colour palette, accessibility) and an…

mohitagw15856/pm-claude-skills · 91 tokens

adhd

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

ADHDMCP · Rule（输出底线 + Agent 行为）

ADHD · 每条回复底线

写码梯子（按序，能停就停）

UI / UX Skills（按需）

MCP 工具（adhd_mcp）

What this file has done since we first saw it

Other cursor rules, from other repositories

explorer-interface-brief

reflection-basic

simplicity

git-workflow

feedback-enhanced

kiss-ponytail