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 agentmods add rules/jerryfish123/adhd-mcp/adhdgit clone --depth 1 https://github.com/JerryFish123/adhd-mcpWhat 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 | $0.00699 | $0.00699 |
| Opus 5 | $0.00349 | $0.00349 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
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 yesterday.
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.
What it actually says
ADHDMCP · Rule（少写 + 输出底线）
本仓库已启用 adhd-mcp（npx adhd-mcp init）。用户不必点名。
Ponytail · 写代码前先爬梯子
Lazy = efficient, not careless. 最好代码是不写的代码。
写任何代码前，在第一档能停就停：
- 这功能真的需要吗？（YAGNI）
- 仓库里已有可复用的吗？
- 标准库够吗？
- 平台原生能力够吗？
- 已安装依赖能覆盖吗？
- 能一行吗？
- 才写 最少必要 代码
梯子前 先理解：读相关代码、trace 真实流程。Bug 修 根因（改共享函数一次），不逐处打补丁。
Not lazy about：信任边界校验、防数据丢失、安全、无障碍、用户明确要求的内容。
ADHD · 每条回复底线
- 能短则短；语言 跟随用户
- 每条回复末尾必须有状态行：
- 先写完正文
- 必须调用 MCP
format_status_footer（传本轮字符数，见下） - 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 %）
- 传
-
理解 <95% → 禁止改代码 / 副作用；只问 一个问题
-
详细 Q&A 流程 → Skill
adhd-qa -
详细输出格式 → Skill
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 |
estimate_context / format_status_footer |
每条回复结尾 |
禁止
- 理解未达标就写代码
- Q&A 阶段一次问多个问题
- 跳过 footer 或省略「本轮 tok」
- 手写 footer（不调用
format_status_footer） - 自动 commit / push（除非用户明确要求）
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.
- yesterday First seen · 65 lines · 699 tokens per session scan A 498215a5e7a5
adhd is a cursor rule published in the GitHub repository JerryFish123/adhd-mcp (0 stars, last pushed 13d ago), licensed MIT. It adds 699 tokens to every session, about $0.0035 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 cursor rules, from other repositories
slushpile
Adversarial job search: pool-anchored fit scoring, adversarial review, channel-conditional verdicts, findings written back to the profile.
feedback-enhanced
Enhanced feedback mechanism with 1-hour timeout - 增强反馈机制，1小时超时.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.