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-robustnessgit 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-robustness)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/rule-of-robustness"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-robustness/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-robustness"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-robustness.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 | $0.00054 | $0.00620 |
| Opus 5 | $0.00027 | $0.00310 |
| Sonnet 5 | $0.00011 | $0.00124 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
rule-of-robustness 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 Robustness
Be liberal in what you accept, rigorous in what you emit. The boundaries of a program are where the world's mess meets your invariants; the input side absorbs reasonable variation, and the output side never inflicts variation on anyone downstream. Robustness is a child of transparency and simplicity — opaque, magic-handling code is brittle, not robust.
When to use
- Designing a parser, deserializer, or boundary that takes data from the outside world
- Designing the format your program writes for someone else to consume
- A teammate proposes "we'll just trust upstream to send valid data"
- A teammate proposes accepting whatever bytes arrive and "doing our best"
Protocol
- On input, accept what you can unambiguously interpret. Trailing whitespace, missing optional fields, slightly off date formats — accept. Define what "unambiguous" means; document it.
- On input, reject what you can't. Cleanly, with a precise error. Never silently coerce, never silently drop, never silently default. Liberal acceptance is not the same as silent corruption ([[crash-early]]).
- On output, emit the canonical form. One representation, one date format, one quoting style, one line ending. Even if the parser accepts more, the emitter writes only the strictest version.
- Never round-trip-degrade. Parsing and re-emitting your own output should be a no-op. If it isn't, the format is over-flexible or the emitter is under-disciplined.
- Version the format. Postel works best when the format itself can evolve; reserve a version field or self-describing header so future-you can tighten or extend without breaking the past.
Red flags (rationalizations to reject)
- "Just be permissive everywhere." — Permissive output is how malformed data spreads through a system. Be picky about what you send.
- "Strict input is user-friendly." — User-hostile, often. A precise error on input is friendly; a noisy refusal of mostly-correct input is not.
- "We'll fix it on the consumer side." — Now every consumer pays. Fix it at the source.
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 · 54 tokens per session scan A 6f43a10a2ee7
rule-of-robustness is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 620 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…