#206206th of 324 in Skills, plugins and prompts
attention-span
Output styles for Claude Code that make replies shorter and answer-first
- Stars
- 1.5k
- License
- AGPL-3.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
33 on 7 Aug 20261,521 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Three markdown output styles for Claude Code (Attention-kind, Spartan, Rundown) that change how Claude words its replies, not how it codes. It ships as a plugin with a /style switcher and user-invoked skills. The README's benchmark reports about 43% shorter output and equal 97% pass rates on 12 coding tasks.
Who it is for: Claude Code users who want terse, skimmable replies
Strengths
- Each style is one markdown file; plugin install is a single /plugin command
- Hidden-test benchmark: 97% pass rate both with and without the style
- Reported ~43% shorter output; about 650 input tokens, cached per session
- Style bodies reusable in Codex AGENTS.md or GEMINI.md via a sed strip
Weaknesses
- Benchmark covers only 12 coding tasks; README does not claim better answers
- Built for Claude Code; other agents need a manual sed-based install
- AGPL-3.0 license may matter if you redistribute modified versions
- Rundown favors scannability over brevity and uses emoji checklists
What it needs
- no GPU
- Needs Claude Code
- Models: Claude Code, Codex, Devin, Antigravity CLI
Quick answers
Is attention-span open source?
Yes. Its code is on GitHub under the AGPL-3.0 license.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |