Borrowing it
Nothing to install: this file belongs to nwiizo/cargo-coupling. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nwiizo/cargo-coupling/main/.agents/skills/balanced-coupling/SKILL.mdgit clone --depth 1 https://github.com/nwiizo/cargo-couplingWrote 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/nwiizo/cargo-coupling/balanced-coupling)<a href="https://agentmods.dev/skills/nwiizo/cargo-coupling/balanced-coupling"><img src="https://agentmods.dev/badge/skills/nwiizo/cargo-coupling/balanced-coupling/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/nwiizo/cargo-coupling/balanced-coupling"><img src="https://agentmods.dev/badge/skills/nwiizo/cargo-coupling/balanced-coupling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.00432 |
| Opus 5.5 | $0.00014 | $0.00173 |
| Sonnet 5.5 | $0.00007 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
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 20d 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.
What it actually says
Balanced Coupling Model
Use the model to judge the cost of coordinated change. It is a conceptual lens; exact detection conditions and reported severities come from the current source.
BALANCE = (STRENGTH XOR DISTANCE) OR NOT VOLATILITY
Qualitative Severity Table
| Pattern | Strength | Distance | Volatility | Interpretation |
|---|---|---|---|---|
| High Cohesion | Strong | Close | Any | Usually appropriate |
| Loose Coupling | Weak | Far | Any | Usually appropriate |
| Acceptable | Strong | Far | Low | Minor concern |
| Global Complexity | Strong | Far | High | Prioritize investigation |
| Local Complexity | Weak | Close | Any | Check whether indirection helps |
Recognition Rules
- Where configured, subdomain volatility represents essential, business-driven change and governs scoring. Raw Git churn feeds accidental-volatility diagnostics; it must not manufacture cascading-change risk for a low-essential-volatility target.
- Binary entrypoints normally have high fan-out and co-change with wired modules.
- Crate-root re-export facades provide a stable interface; their consumers do not automatically depend on volatile implementation details.
- High afferent coupling to a stable central abstraction can be good design.
- Hidden Coupling is temporal co-change without an AST edge. Investigate shared rules or assumptions before diagnosing a defect.
Preserve these distinctions when reviewing or changing detectors. Keep history, thresholds, and subdomain settings comparable; never manipulate them to improve a grade. Include the analysis manifest when interpreting a clean report.
Read model-reference.md only for dimension definitions, subdomain reasoning, or connascence examples. For a particular detector, use explain-issue to locate the implementation.
What ships with it
1 file 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.
- 20d ago Changed · +9 tokens per session 926276b454c1
- 1mo ago Changed · -71 lines · -6 tokens per session fa8d8764cbd0
- 1mo ago First seen · 116 lines · 31 tokens per session scan A 033c670e9099
balanced-coupling is a skill published in the GitHub repository nwiizo/cargo-coupling (116 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 432 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-01.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…