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 agentmods add skills/alexei-led/architect/methodology-balanced-couplingnpx skills add alexei-led/architect --skill methodology-balanced-couplinggit clone --depth 1 https://github.com/alexei-led/architectWrote 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/alexei-led/architect/methodology-balanced-coupling)<a href="https://agentmods.dev/skills/alexei-led/architect/methodology-balanced-coupling"><img src="https://agentmods.dev/badge/skills/alexei-led/architect/methodology-balanced-coupling.svg" alt="Measured on agentmods" 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 | $0.00094 | $0.02587 |
| Opus 5 | $0.00047 | $0.01293 |
| Sonnet 5 | $0.00019 | $0.00517 |
| Haiku 4.5 | $0.00009 | $0.00259 |
Grade A, and why
methodology-balanced-coupling 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 5d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Balanced Coupling
A model for judging whether coupling between components is a problem or not. Coupling is not the enemy — it is what makes a system more than its parts. The question is never "is this coupled?" but "is this coupling balanced?"
This skill summarizes Vlad Khononov's model in our own words and maps it onto
the scorecard. For attribution and licensing, see
references/attribution.md. Do not paste, quote, closely paraphrase, or copy
tables/diagrams from the source.
When to use
Use when judging whether a coupling relationship is a problem — scoring the
coupling_balance dimension, deciding what to flag as structural risk,
designing module boundaries, or sanity-checking a "decouple this"
recommendation. The architecture-review and architecture-design skills reach for
this when they find two components that share knowledge and ask whether that
sharing is balanced. Not for assigning the score itself (architecture-scorecard)
or for executable enforcement (methodology-architecture-fitness).
Skill navigation
- Missing relationship evidence: return to
architecture-reviewfor observed code orarchitecture-designfor proposed boundaries. - Current skill: use
methodology-balanced-couplingto classify strength, distance, volatility, severity, and balancing move. - Next skill: use
architecture-scorecardwhen scoring a review,architecture-designwhen revising target boundaries, orarchitecture-planonly when sequencing an approved balancing move.
The three dimensions
Evaluate the connection between two components, not the components. Three dimensions, each answering a different question.
- Integration strength — how much knowledge the components share, which
sets the likelihood a change in one forces a change in the other. Four
levels, strongest to weakest:
- Intrusive — integration through private internals: shared databases, undocumented APIs, implementation details. Fragile and often implicit; the intruded component may not know it is depended on.
- Functional — components share business requirements and must change together when requirements do. Duplicated business rules across frontend/backend is the classic implicit case.
- Model — components share a domain model; a model change ripples to all sharers.
- Contract — integration through an explicit, stable contract that hides internals (facade, published language, anti-corruption layer, DTOs). Lowest shared knowledge. The goal for high-distance integration.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 225 lines · 94 tokens per session scan A 6f42100c9cf8
methodology-balanced-coupling is a skill published in the GitHub repository alexei-led/architect (2 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 2,587 once invoked, about $0.0005 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
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
map-wayfind
Decision-frontier wayfinding: build and work a durable map of open design decisions BEFORE planning, for large or foggy efforts where /map-plan would force premature decomposition. Use when a task is too big or too vague to decompose — many unknowns, tangled decisions, or "I'm not even sure what to build yet" — and…
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".