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-separationgit 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-separation)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/rule-of-separation"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-separation/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-separation"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/rule-of-separation.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 | $0.00061 | $0.00594 |
| Opus 5 | $0.00030 | $0.00297 |
| Sonnet 5 | $0.00012 | $0.00119 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
rule-of-separation 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 Separation
Policy is what you decide; mechanism is how you carry it out. Policy changes often (user preferences, business rules, defaults); mechanism changes rarely (the actual algorithm, the disk format, the API call). Bind them together and every policy tweak drags the mechanism with it — and vice versa.
When to use
- Designing a tool with a UI: split it before you write either side
- A backend change in feature A requires unrelated UI updates
- Business rules are encoded inside the function that does the work
- You're tempted to bake a default deep into the engine because "everybody uses it that way"
Protocol
- Name the engine. What is the smallest set of operations that does the actual work? Make those callable, parameterised, and indifferent to who calls them or why.
- Name the policy. What changes when a user, config, or business rule changes? Move that to a thin layer that talks to the engine.
- Forbid the engine from knowing about the policy. No "if this is the admin UI, format differently". The engine takes parameters; the policy decides them.
- Make the seam explicit. A function signature, a config schema, a protocol — something you can document and that crash-tests at boundary violations ([[design-by-contract]]).
- Validate by replacing the front end. Swap the UI for a script or a different client. If the engine had to change, the seam was in the wrong place.
Red flags (rationalizations to reject)
- "There's only ever going to be one UI." — Until the API, the cron job, the test harness, or the next platform shows up.
- "Pushing this into config is over-engineering." — Pulling it back out, after the rule has braided itself through the engine, is what's over-engineered.
- "The engine needs to know who's calling for security." — The engine needs an authenticated principal, not a UI. Pass the identity; don't peek at the caller.
Composes with
- [[rule-of-composition]] — the engine is the composable core; the policy is one of many callers.
- [[orthogonality-check]] — policy/mechanism leakage is the most common form of accidental coupling.
- [[reversible-decisions]] — when policy lives in config, you can reverse it without redeploying.
- [[rule-of-least-surprise]] — policy-as-config is also the most honest place to put defaults.
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 · 61 tokens per session scan A 8511e8125daf
rule-of-separation is a skill published in the GitHub repository jonZlotnik/how-to-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 594 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.