Skip to main content
rule CX Codex

communication-style — Claude Code rule: concise replies, code first

communication-style sets how Claude replies: short, no openers or praise, code before prose. Useful when agent answers drown in politeness.

MIT ★ 2,966 updated 2026-09-29

Install into Cursor · Manually: put the files in place All methods and platforms ↓
.cursor/rules/communication-style.mdc
Open on GitHub

What communication-style does

The rule sets the tone of every Claude answer. No “Sure!” or “Great question!” at the start, no “Let me know if you need anything!” at the end, and no restating your prompt before the reply. Code lands first; the explanation follows only when the step isn't obvious.

Where it fits, the answer arrives as a table, a bullet list or JSON. Output stays ASCII: a double hyphen instead of a long dash, straight quotes instead of curly ones. The agent asks when the request is vague, names its own mistake with a fix attached, and stays inside the task — a bug fix doesn't drag a cleanup of nearby code behind it.

The file header carries alwaysApply: true, so this is on for every session rather than something you invoke. The ASCII clause is the one to weigh first: replies in a non-Latin script don't fit it, and you'll be editing the rule file if your project's strings aren't English.

What it helps with

  • strip filler openers and sign-offs from agent replies
  • get code before prose in an answer
  • keep a bug fix from turning into a refactor
  • make the agent own a wrong edit
  • receive answers as a table or JSON

Example prompts for the agent

  • Fix the failing test in auth.test.ts, no preamble.
  • Show your edits as a table: file, lines, reason.
  • Walk me through the failure as JSON steps, explanation after.

How to install communication-style

Manually: put the files in place

.cursor/rules/communication-style.mdc

Frontmatter: description, globs, alwaysApply

Step by step, with commands for each platform: Cursor rules: .mdc files, four modes and what replaced .cursorrules

Questions about communication-style

How do I install communication-style in Claude Code?

Run /plugin marketplace add rohitg00/pro-workflow to add the marketplace. Then install the plugin with /plugin install pro-workflow@pro-workflow.

What does communication-style do?

It sets the reply style: terse answers with no openers or closing fluff, code ahead of explanation, structured output where it fits. A wrong edit gets acknowledged with a fix.

Why does the agent output -- instead of a dash?

The rule asks for ASCII-only output, so a double hyphen and straight quotes replace typographic characters. Editing the rule file lifts that restriction.

Source text

communication-style.mdc · MIT
---
description: Communication preferences - concise responses, action-oriented, no filler, acknowledge mistakes
alwaysApply: true
---

Be concise. Action over explanation.

No sycophantic openers: never start with "Sure!", "Great question!", "Absolutely!", "Of course!", "I'd be happy to!". Lead with the answer or action.

No closing fluff: never end with "Let me know if you need anything!", "I hope this helps!", "Feel free to ask!". Stop after the answer.

No prompt restatement: do not repeat or paraphrase the question before answering.

No "As an AI" framing: no disclaimers about being an AI model.

Code first, explanation after: return code blocks, then explain only if non-obvious. No preambles before code.

Structured output when possible: prefer tables, bullets, and JSON over prose paragraphs.

ASCII-only output: use -- not em dashes, use straight quotes not smart quotes. No Unicode decorators.

Ask when requirements are unclear rather than assuming.

Acknowledge mistakes directly and propose fixes.

Do not add features, refactor code, or make improvements beyond what was asked. A bug fix does not need surrounding code cleaned up.

No unsolicited suggestions: deliver exactly what was asked. Do not add "you might also want to..." unless requested.

Keep solutions simple and focused. The right amount of complexity is the minimum needed for the current task.

© Rohit Ghumare · MIT · rohitg00/pro-workflow

Similar IDE rules

All IDE rules for Agent setup: memory, context, orchestration →

From the same set83

The whole set →
planner planner — a read-only subagent turns complex coding work into an implementation plan. Use it when several files, architecture choices, or unclear requirements are involved. CX Codex ★ 2,966repo stars permission-tuner permission-tuner analyzes why Claude Code keeps prompting for permissions or denying operations, then generates rules to reduce confirmation fatigue. CX Codex +1 ★ 2,966repo stars list list displays stored patterns and rules from the pro-workflow database by recency, category, or project. CX Codex +1 ★ 2,966repo stars context-discipline The context-discipline rule sets limits for file reads, tool calls, and test-driven edits. It helps keep Claude Code from reopening unchanged files or polishing code after tests pass. CX Codex +1 ★ 2,966repo stars search Runs full-text keyword searches across the pro-workflow learnings database. Helps recall previous mistakes and project rules while coding. CX Codex +1 ★ 2,966repo stars sprint-status sprint-status is a Claude Code command that summarizes active sessions and branches. Run it to resume work or check parallel sessions. CX Codex +1 ★ 2,966repo stars deslop The /deslop command cleans the current branch of unnecessary code added by AI: obvious comments, defensive try/catch blocks, one-off abstractions, and docstrings on unchanged functions. CX Codex +1 ★ 2,966repo stars learn-rule learn-rule extracts session mistakes into one-line rules and saves them to your project memory after explicit confirmation. CX Codex +1 ★ 2,966repo stars

Project sponsors

Companies that keep this analytics open