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-generationgit 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-generation)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/rule-of-generation"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-generation/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-generation"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-generation.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 | $0.00046 | $0.00538 |
| Opus 5 | $0.00023 | $0.00269 |
| Sonnet 5 | $0.00009 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
rule-of-generation 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 Generation
If the thing you're about to type follows a rule, type the rule and let a program write the rest. Human-authored repetition is where typos breed and edits go to die. The pattern is the source of truth; the expanded forms are derivatives.
When to use
- About to write the Nth nearly-identical struct, accessor, test case, or migration
- A spec, OpenAPI schema, protobuf, or table already encodes the shape of what you'd write
- A code review reveals copy-paste with small tweaks
- A "table of constants" lives in code and also in docs and also in tests
Protocol
- Find the pattern's authoritative form. Schema, table, list of names, regex — whatever encodes the shape. If it doesn't exist yet, write it first.
- Generate the rest. Codegen, template, macro, build step. The point is that the derivative artifacts can be rebuilt from the source at any time.
- Check in the generator and its output when toolchain reproducibility matters. Check in only the generator when build determinism does.
- Add a check that the output is up to date. A CI step that regenerates and diffs is cheap insurance against drift.
- Stop generating the moment the pattern breaks. If half your cases are special, generation is fighting the domain — fall back to handwriting or split the domain.
Red flags (rationalizations to reject)
- "It's only six cases." — Six cases now, six places to edit forever.
- "Generators are over-engineering." — Six near-identical hand-edits are over-engineering paid in maintenance instead of design.
- "I'll keep them in sync manually." — You won't. Nobody does. That's the whole reason this rule exists.
Composes with
- [[rule-of-representation]] — generation is how you fold a pattern into data and re-derive the code that walks it.
- [[rule-of-minilanguages]] — a tiny DSL for the pattern is often the cleanest source for the generator.
- [[dry-audit]] — generation is the standard cure for the duplication an audit surfaces.
- [[crash-early]] — make the generator fail loudly on a malformed source; never silently emit partial code.
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 · 46 tokens per session scan A c396aad28e35
rule-of-generation is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 538 once invoked, about $0.0002 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…