message-box

A project rule requiring all messages shown to users on stderr—the error output stream—to pass through MessageBox.

In plain words
What is it for?
Use it when implementing user-facing errors, warnings, and informational messages in the command-line application.
Why use it?
It prevents errors and warnings from appearing as unformatted output, including when the program runs in quiet mode.

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/zifeo/lade/message-box
Clone the repo
git clone --depth 1 https://github.com/zifeo/lade

Made for: Cursor.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 362 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 $0.00012 $0.00362
Opus 5 $0.00006 $0.00181
Sonnet 5 $0.00002 $0.00072
Haiku 4.5 $0.00001 $0.00036

Measured 2d ago against content hash c0645745ba25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

message-box 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.

.cursor/rules/message-box.mdc · 43 lines

What it actually says

stderr output must always use MessageBox

Never use eprintln! for user-facing messages. Every message shown to the user — error, warning, or info — must go through message_box::MessageBox.

eprintln! silently bypasses the box, producing bare unformatted output regardless of context (Quiet mode, interactive mode, etc.).

The pattern that broke this

The is_interactive() / UiMode::Quiet flag controls interactive behaviour (countdowns, prompts, sleeps). It must never suppress the MessageBox itself — not for errors, not for warnings.

// ❌ BAD — Quiet mode skips the box entirely
if ctx.is_interactive() {
    message_box::MessageBox::new().error()...print_stderr();
    sleep_or_cancel(5).await;
} else {
    eprintln!("lade: {e}");  // bare, no box
}

// ❌ BAD — same mistake for warnings
if ctx.is_interactive() && !warnings.is_empty() {
    message_box::MessageBox::new().warning()...print_stderr();
    sleep_or_cancel(5).await;
}

// ✅ GOOD — box always; only the interactive parts are gated
let mut mb = message_box::MessageBox::new()
    .error()  // or .warning()
    .paragraph(e.to_string());
if ctx.is_interactive() {
    mb = mb.line("Waiting 5 seconds before continuing... (2x Ctrl-C to cancel)");
}
mb.print_stderr();
if ctx.is_interactive() {
    sleep_or_cancel(5).await;
}
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 · 43 lines · 12 tokens per session scan A c0645745ba25

Subscribe to this mod's changes

message-box is a cursor rule published in the GitHub repository zifeo/lade (127 stars, last pushed 12d ago), licensed MPL-2.0. It adds 12 tokens to every session and 362 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.