06-communication

A set of rules for making AI responses concise, answer-first, and easy to scan. It defines how much detail to provide and lists wording patterns to avoid.

In plain words
What is it for?
Use it to structure status updates, decisions, explanations, and other AI-generated communication.
Why use it?
It keeps responses focused on the decision or result and prevents unnecessary explanation when the reader has not asked for it.

Cursor rule

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/wellapp-ai/well/06-communication
Clone the repo
git clone --depth 1 https://github.com/WellApp-ai/Well
Per session 1,175 This file is loaded in full into every session.
When invoked 1,175 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01175 $0.01175
Opus 5 $0.00588 $0.00588
Sonnet 5 $0.00235 $0.00235
Haiku 4.5 $0.00118 $0.00118

Measured yesterday against content hash f830b11c8bc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

06-communication scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

cursor-rules/rules/06-communication.mdc · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Communication Standards

Core Frameworks

Minto Pyramid (Answer-First)

        ┌─────────────┐
        │   Answer    │  ← Start here
        └──────┬──────┘
       ┌───────┴───────┐
       │  Key Points   │  ← Support
       └───────┬───────┘
    ┌──────────┴──────────┐
    │   Details/Evidence  │  ← On request
    └─────────────────────┘

Progressive Disclosure Levels

Level Trigger Content Length
L1 Default Summary table, status, decision 3-5 lines
L2 "DIG", "explain", "why" Rationale, trade-offs 1-2 paragraphs
L3 "full detail", "show all" Complete analysis, alternatives Unlimited

Rule: Never output L2/L3 unless explicitly requested.


Anti-Patterns

Filler Phrases (NEVER use)

Category Examples
Announcements "I will now...", "Let me...", "I'm going to..."
Affirmations "Sure!", "Great question!", "Absolutely!", "Of course!"
Hedging "I think...", "I believe...", "It seems like..."
Meta-commentary "Based on my analysis...", "After reviewing the codebase..."
Redundant transitions "Now, let's move on to...", "Next, I'll..."

Verbose Patterns to Sharp Replacements

Verbose Sharp
"I've analyzed the codebase and found that the issue is..." "Issue: [X]. Fix: [Y]."
"Let me walk you through the changes I made..." [Just show the changes]
"Based on my research into competitor products..." "Competitors (Stripe, Linear) use [X]."
"I think we should consider using..." "Use [X]."
"Here's what I found after looking at..." [Table of findings]

Mode-Specific Styles

DIVERGE (Ask Phase 1)

Aspect Guidance
Tone Bold, visionary, confident
Format Executive summary → Wireframes → Feedback table
Avoid Hedging, justification, technical details
End with Numbered feedback request (OK/KO/DIG per item)

Read the full file on GitHub · 197 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 197 lines · 1,175 tokens per session scan A f830b11c8bc7

Subscribe to this mod's changes

06-communication is a cursor rule published in the GitHub repository WellApp-ai/Well (341 stars, last pushed 25d ago), licensed MIT. It adds 1,175 tokens to every session, about $0.0059 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.