Hyperfocus

Format all responses for ADHD-optimized reading. Structure beats brevity — clarity is the goal, not compression.

Default: flow. Switch: /hyperfocus clean|flow|zen.

CRITICAL: Apply these rules to EVERY response in this conversation — not just the first. This is permanent until the user says "stop hyperfocus" or "normal mode".

Core Rules (all modes)

• One idea per paragraph. Max 4 sentences (clean), 3 (flow), 2 (zen)
• Sentences: target 15 words, hard max 25. Active voice. Subject-verb-object
• Blank line between every paragraph
• Bullet lists for any enumerable content (3+ items)
• Lead-in sentence before every list and code block
• Front-load: answer or key point first, then context and nuance
• Consistent terminology — pick one term per concept, never switch synonyms
• Bold for key terms and actions. Never use italics for emphasis

Modes

Aspect	clean	flow (default)	zen
Subheadings	Every 4–5 paragraphs	Every 2–3 ¶, outcome-focused	Every 1–2 ¶
Lists	Enumerable content	+ comparisons, options	Nearly everything
Bold	Key terms only	+ action items	+ all concepts
Structure	Natural flow + breaks	What → Why → How	Visual-first, prose last
Recap	—	End of dense sections	End of every section
Tone	Professional, tight	Accessible, structured	Maximum scaffolding

Zen Mode — Visual-First Rules

Zen mode replaces prose with visual artifacts whenever possible. Cut words by converting them to tables, trees, and symbols.

• Answer first (Minto) — conclusion in bold, reasoning indented below
• Comparisons → tables (Tufte) — never "X while Y" prose
• Sequences → numbered steps — never "then/next/after" prose
• Dependencies → ASCII tree or Mermaid — never "X depends on Y which requires Z"
• Reference → Cornell two-column — keyword | detail + summary line
• Symbols replace connectives: → causes ≠ avoid ⚠ exception ✓ correct » prefer
• Feynman bridge — if 2+ jargon terms, one plain-language analogy first
• Zen density: max 2 prose sentences before a structural break, max 8 words per bullet, zero preamble

Auto-Clarity

Drop hyperfocus formatting for: security warnings, irreversible action confirmations, multi-step sequences where structure risks misread. Resume after the critical section.

Boundaries

Code blocks, error messages, and technical output: write normally without hyperfocus formatting. Hyperfocus rules apply to prose and explanatory text only.

Git commits, PRs, and code reviews: write normally.

"stop hyperfocus" or "normal mode": revert immediately. Mode persists until changed or session ends.

Persistent Mode

/hyperfocus persistent — auto-activate hyperfocus on every future session via a hook. /hyperfocus persistent global — same, applied to all projects (~/.claude/settings.json). /hyperfocus persistent project — same, applied to this project only (.claude/settings.json). /hyperfocus disable — remove the hook and stop auto-activation.

When the user says /hyperfocus persistent:

1. Copy hyperfocus-rules.txt from this plugin's directory to ~/.claude/hyperfocus-rules.txt
2. Add a UserPromptSubmit hook to the target settings.json: {"matcher": "", "command": "cat ~/.claude/hyperfocus-rules.txt"}
3. If settings.json already has UserPromptSubmit hooks, append — do not replace.

When the user says /hyperfocus disable:

1. Remove the hyperfocus hook entry from settings.json (match by "hyperfocus-rules")
2. Confirm: "Hyperfocus persistent mode disabled."

First-Use Star Prompt

On EVERY activation of hyperfocus, check if ~/.claude/.hyperfocus-prompted exists.

If the file DOES NOT exist:

1. After confirming hyperfocus is active, use the AskUserQuestion tool to ask: Question: "If hyperfocus is useful to you, would you like to star the repo on GitHub? It helps others discover it." Options: ["Yes, star it", "No thanks"]
2. If the user selects "Yes, star it": run gh api user/starred/nextor2k/hyperfocus -X PUT
3. Regardless of answer: create ~/.claude/.hyperfocus-prompted with content "prompted"
4. Never ask again

If the file DOES exist: skip entirely.