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.
npx skills add jonZlotnik/how-to-agent --skill rule-of-least-surprisegit clone --depth 1 https://github.com/jonZlotnik/how-to-agentWrote 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/skills/jonzlotnik/how-to-agent/rule-of-least-surprise)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/rule-of-least-surprise"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-least-surprise/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/skills/jonzlotnik/how-to-agent/rule-of-least-surprise"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-least-surprise.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 | $0.00058 | $0.00553 |
| Opus 5 | $0.00029 | $0.00277 |
| Sonnet 5 | $0.00012 | $0.00111 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
rule-of-least-surprise 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule of Least Surprise
In interface design, the second-most-creative thing you can do is also the worst. Every novelty costs the reader a lookup, every clever flag a confused user, every reinvented convention a bug at 3am. Match the patterns your users already know — or pay forever.
When to use
- Designing a CLI, library API, REST endpoint, or config file syntax
- Picking flag names, exit codes, default behaviors, or output formats
- Naming a function whose neighbors already have a strong naming convention
- A teammate proposes a "small improvement" to a long-standing idiom
Protocol
- Look first at neighbors. What do the surrounding tools / files / endpoints already do? Whatever it is, that's the prior. You'd better have a reason to deviate.
- Match common idioms.
-vfor verbose,-hfor help, exit 0 for success, JSON over HTTP, ISO-8601 for dates. These are free correctness wins. - Defaults should match expectations. Reading the doc should confirm what the reader already guessed, not surprise them. If your defaults need explanation, they're wrong.
- Reserve creativity for the actual novelty. Be conventional on the surface; be original where you genuinely solve a new problem. Don't burn the surprise budget on syntax.
- Cross-check with someone who hasn't read your README. If they can guess the flags and outputs from prior experience, you've succeeded.
Red flags (rationalizations to reject)
- "Our way is better." — Maybe, marginally. The cost of forcing every user to relearn dwarfs the gain.
- "It's clearly documented." — Documentation is the consolation prize for an interface that failed to be obvious.
- "Consistency is the hobgoblin of little minds." — In interface design it is the friend of every human who has to remember which tool is which.
Composes with
- [[rule-of-separation]] — policy layers (defaults, flag wiring) are where convention conformance lives.
- [[design-by-contract]] — explicit contracts make conventional behavior testable.
- [[broken-windows]] — one surprising flag invites another; conventional surfaces stay conventional.
- [[reversible-decisions]] — interface conventions, once shipped, are among the hardest decisions to reverse.
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.
- 12d ago First seen · 37 lines · 58 tokens per session scan A 611c08799414
rule-of-least-surprise is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 553 once invoked, about $0.0003 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.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.