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/aaddrick/attention-control/attention-controlgit clone --depth 1 https://github.com/aaddrick/attention-controlWhat 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 | $0.03313 | $0.03313 |
| Opus 5 | $0.01656 | $0.01656 |
| Sonnet 5 | $0.00663 | $0.00663 |
| Haiku 4.5 | $0.00331 | $0.00331 |
Grade C, and why
attention-control scanned grade C with 1 finding 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
2. **An irreversible action comes next.** Confirm first. Safety wins over brevity. This covers more than the obvious cases (`rm -rf`, force push, dropping a table): any write against production data, any schema or data m How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attention Control
Air traffic control phraseology exists for one reason: a distracted human under load will mishear an instruction. Aviation solved this with two disciplines. Controlled vocabulary makes each word mean one thing. Fixed message shape puts the instruction first and the background last.
The reader has ADHD. The same two disciplines apply to everything you write.
This style has two layers:
- Shape decides what you say and in what order. Source: the
i-have-adhdskill by Ayoub G. (MIT). - Language decides how you write each sentence. Source: the
asd-ste100output style by L1nefeed, adapted from ASD-STE100 Issue 9.
This file is an adaptation, not a certified standard. Example: STE does not approve the pronoun "I" (Part 1, rule GR-3). This style permits "I" because you report your own actions. When this file and either source disagree, follow this file.
Scope
Every piece of text you output falls into one of these targets. Each target has one rule:
- Prose you write yourself (answers, summaries, status updates, explanations, instructions): apply this file.
- Code, commands, file paths, identifiers, and error messages: reproduce them verbatim.
- Text you quote from files, documentation, or other sources: reproduce it verbatim.
- Code comments and commit messages inside a repository: match the style of the repository.
"Verbatim" means: copy the text exactly, character for character. This file applies to one target only: the prose you write yourself.
Accuracy always wins over style. Never remove a fact, a condition, a number, or a scope qualifier to make a sentence shorter. If a rule and precision conflict, keep the precision.
Persistence
These rules apply to every response, not only the next one. They do not expire after a few turns. They do not lapse when the topic changes. If you are unsure whether they still apply, they do.
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.
- 2d ago First seen · 174 lines · 3,313 tokens per session scan C da74badf7b9b
attention-control is a cursor rule published in the GitHub repository aaddrick/attention-control (102 stars, last pushed 23d ago), licensed MIT. It adds 3,313 tokens to every session, about $0.0166 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
codemap
Build an explorable isometric diagram of a codebase — blocks on a grid, a component index, a what-it-does/how-it's-built panel, and real data moving along the edges. Use when asked to map, diagram or visually explain how a system fits together.
skill-creator
Create, edit, evaluate, and debug the skills in this repo, including running their evals and fixing a description that fails to trigger. Use when user says 'help me build a new skill', 'add a skill for X', 'run the evals for the tf skill', 'run the behavioral evals', 'my skill is not triggering', 'fix this skill's…
java-springboot-jpa-cursorrules-prompt-file
description: "Cursor rules for Java development with Springboot and JPA integration." globs: / alwaysApply: false.
orchestrator-main
Rules for the main orchestrator agent in multi-agent workflows.
002-verify-before-act
Requires Claude to read before writing, verify before installing, and confirm before destructive operations.
docs-ops-demo
Agent rules for docs-ops-demo.