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-optimizationgit 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-optimization)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/rule-of-optimization"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-optimization/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-optimization"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-optimization.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 | $0.00051 | $0.00637 |
| Opus 5 | $0.00026 | $0.00318 |
| Sonnet 5 | $0.00010 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
rule-of-optimization 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 11d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule of Optimization
Performance work without measurement is folklore. Code that's been optimized for a bottleneck it doesn't have is just more complicated code with worse readability and no benefit. Measure, locate the actual bottleneck, fix it at the highest possible level, then stop.
The "prototype before polishing" half of the Rule of Optimization is covered by [[prototype-to-learn]]. This skill is about what to do after the working prototype, when speed becomes the question.
When to use
- About to add a cache, a pool, an inlined hot path, or hand-rolled assembly
- A reviewer says "this would be faster if…"
- A piece of code is being kept ugly because it's "for performance"
- A frontend perception of slowness is being blamed on the wrong layer
Protocol
- Don't just do something — stand there. First confirm there is a real performance problem, with numbers, against a budget. "Feels slow" is not a budget.
- Profile the actual workload. A representative input, on representative hardware, with the actual data shape. Synthetic micro-benchmarks lie.
- Find the global win first. Algorithmic improvements (O(n²)→O(n log n)), avoided work (caching, batching, lazy eval), structural changes (overlap, parallelism). Local micro-optimizations come last and gain little.
- Change one thing; remeasure. Optimizations interact. Two "improvements" can cancel or harm. Re-run the profile after every change.
- Stop at the budget. Once you've met the target, the optimization is over. Don't keep tuning for sport — every extra line of fast-but-clever is a future maintenance bill.
Red flags (rationalizations to reject)
- "It'll be slow at scale." — Maybe. Measure at scale or build a benchmark that simulates it. Don't optimize for an imaginary future load.
- "Premature optimization is the root of all evil, but…" — There is no "but". Make it correct, measure, then optimize what shows up.
- "This micro-optimization is harmless." — It costs readability now and pays performance only if the line is hot. Profile says so, or it didn't happen.
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.
- 11d ago First seen · 39 lines · 51 tokens per session scan A db23844bd44f
rule-of-optimization is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 637 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.