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.
git clone --depth 1 https://github.com/zifeo/ladeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/zifeo/lade/message-box)<a href="https://agentmods.dev/rules/zifeo/lade/message-box"><img src="https://agentmods.dev/badge/rules/zifeo/lade/message-box/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/zifeo/lade/message-box"><img src="https://agentmods.dev/badge/rules/zifeo/lade/message-box.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00011 | $0.00387 |
| Opus 5.5 | $0.00004 | $0.00155 |
| Sonnet 5.5 | $0.00002 | $0.00077 |
| Haiku 4.5 | $0.00001 | $0.00039 |
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 22d 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.
What it actually says
stderr: box for attention, report for results
Never use eprintln! from command code. User-facing stderr goes through
message_box.
MessageBoxwhen the user must notice: errors, warnings, disclaimers, pre-exec / pre-tool access failures, a new Lade release. The bordered box is the point.Reportfor the result of a verb (lade setup,lade update,lade teardown,lade hook enable, add/remove, upgrade already current). Bold headings and colour when the terminal allows it. No border.
UiMode / is_interactive() gates prompts, countdowns, and sleeps. It
must never suppress a MessageBox.
// ❌ BAD — setup success in a box
MessageBox::new().info().line("pre-exec this shell").print_stderr();
// ✅ GOOD — command result
Report::new().heading("pre-exec this shell").dim("Wraps commands you type.").print();
// ✅ GOOD — attention (pre-exec failure, or a new Lade release)
MessageBox::new().error().paragraph(e.to_string()).print_stderr();
Do not box lade setup / lade update success. After that report, if a
newer Lade binary is available, emit a MessageBox (upgrade::nudge_if_available).
Do not nag on lade set: stdout is the shell protocol.
Live setup / update: one tracker row per step (spinner, then ✔︎), same
machinery as provider resolve. Mise logs update the current row. Never
inherit the child stdio. mise env --json-extended stays captured and quiet.
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.
- 22d ago Changed · -3 lines · -1 tokens per session b798cd7fb347
- 1mo ago First seen · 43 lines · 12 tokens per session scan A c0645745ba25
message-box is a cursor rule published in the GitHub repository zifeo/lade (135 stars, last pushed 4d ago), licensed MPL-2.0. It adds 11 tokens to every session and 387 once invoked, about $0.0000 per session on Opus 5.5. 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.
Other cursor rules, from other repositories
mise
Use mise run fix and build only for agent work.
github-workflow
GitHub invariants — standard flow on listed use cases; no issue spam; tick linked checklists before merge.
skill-selection
Pick the fewest skills for this task. Core lifecycle for non-trivial work; extras only on a matching signal. Catalog is using-agent-skills, not this rule.
next
Next.js roof. Version-matched docs for THIS app. App vs Pages from the tree.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.