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-minilanguagesgit 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-minilanguages)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/rule-of-minilanguages"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-minilanguages/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-minilanguages"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-minilanguages.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 | $0.00055 | $0.00688 |
| Opus 5 | $0.00028 | $0.00344 |
| Sonnet 5 | $0.00011 | $0.00138 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
rule-of-minilanguages 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule of Minilanguages
Some problems are most honest when expressed as a tiny language. A pattern matcher, a build description, a routing table — when the natural way to state the rules is as rules, code that pretends to be procedural is fighting the domain. A well-chosen minilanguage compresses a class of problems into something readable, declarative, and extensible.
When to use
- Users (or you) keep writing the same shape of expression by hand
- A config file is sprouting conditionals, computed values, or shared fragments
- A domain is best described as patterns and transformations, not as steps
- You're about to write a parser ad hoc — for the third time
Protocol
- Confirm the domain has shape. A minilanguage pays off only when the same kinds of expressions repeat. One-offs are config; recurring patterns are language.
- Choose the smallest level of power. Pick the least expressive form that fits — keyword=value before lists before expressions before Turing-complete. Power is a liability; you can't take it back.
- Borrow before inventing. Existing minilanguages (regex, jq, awk, JSON-Pointer, SQL subset, glob, expr) often fit. Inventing means you also own the parser, errors, docs, and corner cases.
- Make it textual and editable ([[rule-of-textuality]]). Even a binary-backed engine deserves a textual surface.
- Resist creep. When users ask for "just one more feature", first see if existing primitives compose to do it. Macros and "just a quick if" are how minilanguages turn into ad-hoc programming languages without anyone deciding to.
- Test the design by reading it. Write example programs first; if they don't read clearly, revise the grammar and repeat before you build a parser.
Example
# routing table as a minilanguage — declarative, least power
GET /users/:id -> users.show
POST /users -> users.create
Red flags (rationalizations to reject)
- "We just need to add an
if." — That's the moment a configuration becomes a programming language and starts owing you everything a language owes its users. - "It's just a quick parser." — Quick parsers are how project-specific languages with no error messages happen.
- "Macros will make it cleaner." — Macros postpone complexity; they don't remove it. Beware.
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 · 46 lines · 55 tokens per session scan A fd836f0efd1e
rule-of-minilanguages is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 688 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…