Skip to content
HomeNewsDigestsConceptsGuidesToolbox
AboutSubscribeUA
Subscribe

AI Today Brief

The daily AI-engineering brief. Built in public. EN · UA.

XTelegramLinkedInYouTubeRSS

Follow AI Today Brief on LinkedIn for daily AI-engineering updates and the weekly “5 shifts that changed how developers work” PDF.

Explore

NewsDigestsConceptsGuides

Company

SubscribeAdvertiseAbout

Legal

Editorial policyAI disclosurePrivacyTerms

© 2026 AI Today Brief. All rights reserved.

  1. Home/
  2. News/
  3. Tools & releases/
  4. Open-Source Claude Code Skill Strips Conversational Pleasantries for Action-First Outputs
Tools & releases

Open-Source Claude Code Skill Strips Conversational Pleasantries for Action-First Outputs

A community-built Claude Code skill titled i-have-adhd formats terminal assistant responses into concise, numbered steps. It eliminates pleasantries, surfaces code modifications instantly, and provides concrete time estimates to reduce context bloat.

September 11, 2026· 4 min read
OKCurated by Oleksandr Kuzmenko, AI Product Engineer·Updated September 11, 2026·Sources cited on every story
AI-assisted · editor-reviewed·How we use AI
Open-Source Claude Code Skill Strips Conversational Pleasantries for Action-First Outputs

Impact: Medium

Why it matters

Install this plugin to stop your CLI coding assistant from generating conversational filler and get straight to executable code diffs.

TL;DR

  • 01The i-have-adhd plugin strips conversational filler and pleasantries from Claude Code responses.
  • 02Forces agents to output concrete file diffs, line numbers, and minute-level time estimates first.
  • 03Easily installed via the Claude Code plugin marketplace or forked to tailor system prompt guidelines.

Key facts

Target tool
Claude Code CLI plugin ecosystem
Foundation
Adapted from The Adult ADHD Tool Kit

Eliminating Assistant Conversational Overhead

The i-have-adhd open-source skill targets a common friction point in terminal-first coding: assistant fluff. Instead of wrapping code suggestions in multiple paragraphs of discursive text, the plugin constrains Claude Code to a structured, action-first response pattern:

  • Direct executable actions and file targets (e.g., src/auth.ts:42)
  • Numbered, minimal steps with zero filler
  • Clear failure branches: instructing the user exactly what output to paste if a test errors
  • Exact minute estimates rather than vague temporal markers

Installation and Customization

The plugin connects natively to the Claude Code plugin marketplace. Developers can install the default ruleset directly from the CLI or fork the repository to adjust formatting rules in skills/i-have-adhd/SKILL.md.

Try it in 2 minutes

claude plugin install i-have-adhd@i-have-adhd

bash

✓ When to use

  • When running fast terminal bug-fixing and refactoring sessions inside Claude Code.
  • When looking to save context window tokens by eliminating conversational pleasantries.

✕ When NOT to use

  • Do not use when you need open-ended conceptual explanations or architectural brainstorming.
  • Avoid if you rely on detailed background rationale alongside code snippets.

What to do today

  • →Install the plugin using `claude plugin install i-have-adhd@i-have-adhd` and test the `/i-have-adhd` command in your terminal session.
#Claude Code#Claude

Sources

  • GitHub: i-have-adhd
ShareShare on XShare on LinkedIn
← Previous storyResearchers Uncover Code Injections and Secret Exfiltration in Third-Party Large Language Model RoutersNext story →Cursor Launches Projects to Replace Disconnected Agent Chats with Persistent Threads

Related stories

  • Tools & releasesShopify Replaces React Native with Swift and Kotlin via Coding Agents
  • Tools & releasesCursor Launches Projects to Replace Disconnected Agent Chats with Persistent Threads
  • Tools & releasesOpenAI Halts New Two-Hundred-Dollar Pro Subscriptions Following Surging Astra Demand
  • Tools & releasesHugging Face Rebuilds AUTOMATIC1111 as Gradio Workflow and Model Context Protocol Server

Email digest

Get the morning AI brief

One email a day — the stories that matter for engineers, founders and tech leads. Human-edited, with links to primary sources.

  • ✓120+ sources scanned daily
  • ✓Edited by a human
  • ✓1 email per day
  • ✓EN + UA

By subscribing you agree to the privacy policy.