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 orthogonality-checkgit 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/orthogonality-check)<a href="https://agentmods.dev/skills/jonzlotnik/how-to-agent/orthogonality-check"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/orthogonality-check/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/orthogonality-check"><img src="https://agentmods.dev/badge/skills/jonzlotnik/how-to-agent/orthogonality-check.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 | $0.00520 |
| Opus 5 | $0.00026 | $0.00260 |
| Sonnet 5 | $0.00010 | $0.00104 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
orthogonality-check 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orthogonality Check
Orthogonal components change independently. The test is simple: change one thing; count what else must move. If unrelated areas have to follow, the design is coupled, and every future change pays that tax.
When to use
- Designing a new module, service, or class
- Reviewing a diff that spans modules you thought were unrelated
- A bug in feature A is fixed by changing feature B
- Tests fail in distant subsystems when one file changes
Protocol
- Name the change. "Switch the user store from SQL to KV." "Change the rate limit window."
- List what must move with it. Be ruthless — include tests, docs, configs, types, mocks, fixtures.
- Cluster the impacts. Same module / adjacent module / unrelated module. Anything in the third bucket is a coupling smell.
- Trace each unrelated impact to its cause — shared mutable state, leaked types, implicit ordering, knowledge duplication ([[dry-audit]]), reaching into private guts.
- Decide: refactor the seam (introduce an interface, a parameter, an event), or accept and document the coupling. Don't silently absorb it.
Quick coupling indicators
- Two modules import each other (cycle)
- A "utility" file is imported by half the codebase and edited every sprint
- Changing a database column requires UI edits
- A test in module A breaks when module B is refactored
Red flags (rationalizations to reject)
- "It's just one extra change, no big deal." — One extra change, every time, forever.
- "They're naturally related." — Maybe. Often "naturally related" means "I never separated them".
- "Decoupling would be over-engineering." — Coupling is the over-engineering; you're paying compound interest on it.
Composes with
- [[dry-audit]] — shared knowledge is the most common coupling cause.
- [[reversible-decisions]] — orthogonal designs keep more decisions reversible.
- [[design-by-contract]] — explicit contracts at module seams are the cheapest way to decouple.
- [[broken-windows]] — quietly worsening coupling is the canonical broken window.
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 · 44 lines · 51 tokens per session scan A 94ea26216140
orthogonality-check 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 520 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…