cursor

cursor is a cursor rule for coding agents from SteinsFu/my-adhd-caveman. It costs 240 tokens per session, scanned A, original, MIT.

An always-on instruction set for Cursor, a code editor with AI features, that keeps responses terse, numbered, and focused on the next action.

In plain words
What is it for?
It helps present commands, progress updates, safety notes, code changes, and a small next step in a compact format.
Why use it?
It makes coding-agent replies easier to scan and gives multi-step work a consistent structure.

Cursor rule

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.

agentmods
npx agentmods add rules/steinsfu/my-adhd-caveman/cursor
Clone the repo
git clone --depth 1 https://github.com/SteinsFu/my-adhd-caveman

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 cursor

README.md
[![agentmods](https://agentmods.dev/badge/rules/steinsfu/my-adhd-caveman/cursor.svg)](https://agentmods.dev/rules/steinsfu/my-adhd-caveman/cursor)
Your own site
<a href="https://agentmods.dev/rules/steinsfu/my-adhd-caveman/cursor"><img src="https://agentmods.dev/badge/rules/steinsfu/my-adhd-caveman/cursor.svg" alt="Measured on agentmods" height="20"></a>
Per session 240 This file is loaded in full into every session.
When invoked 240 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00240 $0.00240
Opus 5 $0.00120 $0.00120
Sonnet 5 $0.00048 $0.00048
Haiku 4.5 $0.00024 $0.00024

Measured 3d ago against content hash c5eb30ef38f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor 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 3d 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.

rules/cursor.mdc · 18 lines

What it actually says

Follow the my-adhd-caveman skill. If installed, read SKILL.md (often ~/.cursor/skills/my-adhd-caveman/SKILL.md). If missing, follow the policy below.

Policy: ADHD shape, caveman diction. Numbered terse steps. Action first.

  1. First line = next action (command, path, or snippet).
  2. Number multi-step work. Cap 5. One next action at the end, doable in under two minutes.
  3. Progress = one line (Step 3/5: schema done), not a recap.
  4. Drop fluff, articles, pleasantries. Fragments OK. No invented abbreviations. No causal arrows.
  5. Safety / irreversible ops: full sentences for that block, then resume.
  6. Code, commits, PRs, docs: normal prose.

Off only: stop adhd-caveman / stop my-adhd-caveman / normal mode.

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. 3d ago First seen · 18 lines · 240 tokens per session scan A c5eb30ef38f9

Subscribe to this mod's changes

cursor is a cursor rule published in the GitHub repository SteinsFu/my-adhd-caveman (2 stars, last pushed 15d ago), licensed MIT. It adds 240 tokens to every session, about $0.0012 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.