user-facing-language

Writing rules for user-facing text such as documentation, interface copy, and error messages. They favor direct, specific language that explains real behavior without empty promotional claims.

In plain words
What is it for?
Use them when writing or reviewing READMEs, documentation, website copy, interface text, and error messages.
Why use it?
They help turn technical information into clear text that users can understand and trust.

Cursor rule for Cursor

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/technickai/claude_telemetry/user-facing-language
Clone the repo
git clone --depth 1 https://github.com/TechNickAI/claude_telemetry

Made for: Cursor.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,012 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00020 $0.01012
Opus 5 $0.00010 $0.00506
Sonnet 5 $0.00004 $0.00202
Haiku 4.5 $0.00002 $0.00101

Measured 2d ago against content hash 2d309ea406f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

user-facing-language 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 2d ago.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/user-facing-language.mdc · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User-Facing Language Guide

Write for capable, intelligent users. Make them feel respected, capable, confident, understood, and excited.

Quality bar: Apple-level attention. Every word earns its place.

Voice

Be authentic. Explain something real, not sell something imaginary. "Exports to CSV in under 2 seconds" builds trust. "Fast and efficient" says nothing.

Be direct. Say what you mean. Cut unnecessary words.

Be confident. You built something real, so own it. Avoid hedging with "might," "could," or "potentially." If it saves time, say how much.

Be specific. Concrete details matter. "Handles codebases up to 1M lines" beats "Scales well."

Language Patterns

Use "we" for the team: "We built this to solve the N machines problem." Use "you" for users: "You configure it once, then it runs automatically." Use imperatives for instructions: "Install the package. Set your API key."

What Not to Write

AI Clichés

The "it's not just X, it's Y" pattern appears constantly in AI-generated content. Never use it.

✗ "It's not just a code editor, it's a complete development environment"
✗ "This isn't just about speed, it's about transforming your workflow"
✗ "If 2024 was the year of X, 2025 will be..."
✗ "Imagine a world where..."
✗ "Let's dive in..."

✓ "A code editor with integrated debugging and deployment"
✓ "Processes 10,000 records in 2 seconds instead of 5 minutes"

CRITICAL Means Something Dies

AI marks everything as CRITICAL. Reserve this word for when something actually breaks without it.

✗ "CRITICAL: Read this section"
✗ "CRITICAL: Follow these best practices"
✗ "CRITICAL: Understand the architecture"

✓ "CRITICAL: Set ANTHROPIC_API_KEY or Claude Code won't start"
✓ "CRITICAL: Back up data before running - this operation is destructive"

CRITICAL means the system fails, data is lost, or security is compromised. Don't use it for recommendations, best practices, or things that are merely helpful. Most things aren't critical.

Format

Read the full file on GitHub · 148 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. 2d ago First seen · 148 lines · 20 tokens per session scan A 2d309ea406f4

Subscribe to this mod's changes

user-facing-language is a cursor rule published in the GitHub repository TechNickAI/claude_telemetry (30 stars, last pushed 10mo ago), licensed MIT. It adds 20 tokens to every session and 1,012 once invoked, about $0.0001 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.