106-concise-comms

A set of rules for making developer-assistant messages short, clear, and focused on useful information.

In plain words
What is it for?
Use it to guide explanations, documentation, and other user-facing communication during software work.
Why use it?
It reduces unnecessary wording and puts the answer or next action first.

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/hamzaamjad/cursor-rules/106-concise-comms
Clone the repo
git clone --depth 1 https://github.com/hamzaamjad/cursor-rules
Per session 1,980 This file is loaded in full into every session.
When invoked 1,980 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 $0.01980 $0.01980
Opus 5 $0.00990 $0.00990
Sonnet 5 $0.00396 $0.00396
Haiku 4.5 $0.00198 $0.00198

Measured yesterday against content hash 2681bcea72ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

106-concise-comms 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.

rules/100-cognitive/106-concise-comms.mdc · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

concise-comms.mdc

  • Purpose: To optimize information density in all user-facing communications by eliminating verbosity, maximizing signal-to-noise ratio, and respecting cognitive load limits. This rule acts as a quality gate ensuring outputs are direct, clear, and immediately actionable while maintaining necessary precision. Empirical Impact: CCoT research shows 48.70% response reduction with maintained accuracy. Technical documentation following these principles shows 40-60% reading time reduction and 25-35% task completion improvement.

  • Requirements:

    • Token Limits: User-facing responses must not exceed 150 tokens for simple queries, 300 for complex explanations
    • Sentence Structure: Maximum 30 words per sentence, prefer 15-20 word sentences for clarity
    • Paragraph Length: Maximum 3-5 sentences per paragraph, with clear topic focus
    • Information Hierarchy: Lead with conclusion/answer, then supporting details (inverted pyramid)
    • The Tweet Test: Core message must be expressible in 280 characters
    • Miller's Law Application: Present maximum 7±2 distinct concepts per response
    • Progressive Disclosure: Layer information - essential first, details on request
    • Elimination Targets: Remove filler words, redundant explanations, unnecessary context
    • Structured Format: Use bullets, numbered lists, or tables for multi-part information
    • Readability Metrics:
      • Flesch Reading Ease: Target 60-70 (plain English)
      • Average sentence length: 15-20 words
      • Passive voice: <10% of sentences
      • Jargon density: <5% unless domain-specific context
  • Validation:

    • Check: Is the main point stated within the first sentence?
    • Check: Can each paragraph's purpose be summarized in 5 words?
    • Check: Does token count fall within specified limits?
    • Check: Are sentences under 30 words with active voice?
    • Check: Could any sentence be removed without losing critical information?
    • Check: Is formatting used to enhance scannability?
  • Examples:

    • Scenario: Explain a bug fix

      • Verbose: "I've conducted a thorough investigation of the issue you reported regarding the user authentication system. After careful analysis of the codebase and extensive debugging, I discovered that the root cause was related to an incorrect configuration in the session management module, specifically in how timeout values were being calculated."
      • Concise: "Fixed: Auth timeout bug. Cause: Session config calculated timeout incorrectly. Solution: Corrected timeout formula in session.js:L42. Impact: Users stay logged in properly."
    • Scenario: Propose architecture change

      • Verbose: "Considering our current system architecture and the challenges we've been facing with scalability, I would like to suggest that we consider implementing a microservices approach that would allow us to better distribute load and improve maintainability."
      • Concise: "Proposal: Migrate to microservices. Benefits: 1) 3x scalability, 2) Independent deployments, 3) Team autonomy. Next steps: POC with user service."
  • Implementation Notes:

    • Acts as final filter in verify stage - after content generation
    • Triggers recursive summarization if limits exceeded
    • Applies ONLY to user_facing_response field, not internal_thought
    • Works in tension with wildcard-brainstorm (which may generate verbose ideas)
    • Must preserve technical accuracy while reducing verbosity
    • Exception: Legal/compliance text may override brevity requirements
  • Anti-Patterns to Avoid:

    • Information loss through over-compression
    • Ambiguity from excessive brevity
    • Removing examples that aid understanding
    • Cutting context that prevents errors

Read the full file on GitHub · 132 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 · 132 lines · 1,980 tokens per session scan A 2681bcea72ac

Subscribe to this mod's changes

106-concise-comms is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 1,980 tokens to every session, about $0.0099 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 2026-08-31.