attention-control

Install

Claude Code is the only agent here with a native output style slot. Run these two commands in your terminal:

claude plugin marketplace add aaddrick/attention-control

claude plugin install attention-control@attention-control

Then run /config, select Output style, and pick Attention Control. It takes effect after /clear or the next session.

To skip the picker, add outputStyle to ~/.claude/settings.json. It is a top-level key. It does not go inside env, permissions, or any other block:

{
  "model": "opus",
  "env": { "EXAMPLE_VAR": "1" },
  "outputStyle": "Attention Control"
}

model and env stand in for keys you may already have. Keep them. Add the outputStyle line beside them.

For one session instead of every session, use the skill the plugin also ships:

/attention-control:attention-control

Say "stop attention control" to turn it off.

Codex has no output style slot, so the rules ship as a skill.

codex plugin marketplace add aaddrick/attention-control --ref main

codex plugin add attention-control@attention-control

Inside Codex, /plugins opens the plugin browser instead.

Start a new thread, then type the skill:

$attention-control:attention-control

Codex prefixes a plugin skill with the plugin name. Say "stop attention control" to turn it off. For every turn instead, put the always-on snippet from INSTALL.md in ~/.codex/AGENTS.md.

See INSTALL.md. None of them has an output style slot, so the rules ship as a skill, a rules file, or an AGENTS.md block. On a skill route, type /attention-control and say "stop attention control" to turn it off.

What it does

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.

This style applies both disciplines to your coding agent. The agent leads with the action you can run, and writes each sentence so one word means one thing.

The style targets one reader: a reader with ADHD. That reader is where the shape rules come from. See Why the shape rules exist.

What changes

Before

Great question! Let me take a look. It seems like the auth flow has a few moving pieces here. Looking at src/auth.ts, the token verification logic could possibly be utilizing a deprecated API — the verifyToken function around lines 42-58 has been implemented against an older jsonwebtoken signature. One approach that might be considered would be updating the package and refactoring that function. By the way, your dependency versions in general could probably use a review at some point. Hope this helps! Let me know if you'd like me to dig deeper into any of this.

After

Run npm install jsonwebtoken@latest.

I changed src/auth.ts:47. verifyToken now names the algorithm:

jwt.verify(token, secret, { algorithms: ["HS256"] }, callback);

Run npm test -- auth.spec.ts. It takes about 10 seconds.

The old call named no algorithm. jsonwebtoken v9 rejects an unsigned token unless you pass algorithms: ["none"].

Next: paste the first failing line if a test fails.

The two layers

Shape decides what you say and in what order. 11 rules:

1. Lead with the next action.
2. Do the work you own.
3. Number multi-step work.
4. End with one concrete next action.
5. Suppress tangents.
6. Restate state every turn.
7. Give time estimates in concrete units.
8. Show what now works.
9. State errors flat.
10. Cap lists at 5 items.
11. No preamble, no recap, no closer.

Language decides how each sentence reads. The short version:

• One word, one meaning. One action, one verb. No rotating synonyms.
• Standard verbs: "check", "make sure", "start", "stop", "use", "show", "find", "change", "remove", "need".
• Active voice. Name the actor.
• Simple tenses only. No perfect tense, no auxiliary stacks.
• 20 words per instruction, 25 per explanation. Noun clusters capped at 3 words.

Full text: output-styles/attention-control.md.

Why the shape rules exist

Five facts about ADHD reading drive all 11 shape rules. Each fact below names the rules it produces.

Two more rules protect attention itself. Rule 5 suppresses tangents, so one open thread stays one open thread. Rule 11 removes the preamble and the closer, so the answer starts on line 1.

This is why the style is not "be terse". Terseness that drops the command, the number, or the condition costs the reader a round trip, and a round trip costs the thread. Rule 9 follows from the same logic: an error gets a location, a cause, and a fix, with no "Uh oh" in front of it. Alarm is not information, and it competes with the information for the same attention.

You need no ADHD diagnosis for this to help. A tired reader, a reader on a phone, and a reader with 40 open tabs all read the same way.

What it leaves alone

Four targets, one rule each. Code, commands, file paths, identifiers, and error messages stay verbatim. Quoted text stays verbatim. Code comments and commit messages match the style of the repository around them. Only the prose the agent writes itself follows this style.

Those are instructions, not a lock. An output style is system prompt text, and nothing outside the model enforces it. Treat the boundary as a strong default, and check the output when it matters.

Accuracy beats brevity. A rule never removes a fact, a number, a condition, or a scope qualifier. A hedge that carries real uncertainty stays.

Evals

The harness compares response quality against an unstyled baseline. It does not measure length.

python3 scripts/run_evals.py validate

python3 scripts/run_evals.py plan --trials 3

24 cases, 6 scored dimensions, and a release gate that blocks a candidate that regresses correctness or safety.

The judge is the weak point, so the harness targets it. blind hides the condition and balances the positions. The judge scores every group twice with the order reversed, then reports how often the two passes disagree. The runner runs in an empty directory and reads none of your config. Design notes and the measurements behind them: evals/README.md.

Tune it

Fork, edit output-styles/attention-control.md, then regenerate every agent-specific copy:

python3 scripts/sync_style.py

Swap your copy in, one command at a time:

claude plugin uninstall attention-control

claude plugin marketplace remove attention-control

claude plugin marketplace add <your-username>/attention-control

claude plugin install attention-control@attention-control

Credits

This style combines two existing works. Neither author takes part in this project.

Shape layer: i-have-adhd by Ayoub G. (MIT). The eval harness derives from the same project