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 xonovex/platform --skill connascence-guidegit clone --depth 1 https://github.com/xonovex/platformWrote 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/xonovex/platform/connascence-guide)<a href="https://agentmods.dev/skills/xonovex/platform/connascence-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/connascence-guide/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/xonovex/platform/connascence-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/connascence-guide.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 | $0.00111 | $0.00727 |
| Opus 5.5 | $0.00044 | $0.00291 |
| Sonnet 5.5 | $0.00022 | $0.00145 |
| Haiku 4.5 | $0.00011 | $0.00073 |
Grade A, and why
connascence-guide 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 1mo 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connascence: a Precise Coupling Vocabulary
Grade a seam by naming its worst coupling and its strongest connascence, then weaken or localize it: "tight/loose" is unactionable.
Essentials
- Name the connascence, don't say "tight" - classify the form and rate strength/locality/degree, see references/connascence.md
- Two moves: weaken and localize - rule of degree (strong→weak forms) and rule of locality (distance→weakness), see references/connascence.md
- Push every seam down the coupling ladder - content→common→control→stamp→data, worst to best, see references/coupling-ladder.md
- Aim for functional cohesion - one job per module; temporal cohesion is the package-by-layer trap, see references/cohesion-ladder.md
- Don't reach through strangers - Law of Demeter as the call-site detector for content coupling, see references/law-of-demeter.md
Gotchas
- "Tightly coupled" is not actionable: name the connascence form and the coupling rung, then you know the fix.
- Strong connascence is fine inside one module; it's only a problem across a boundary (rule of locality).
- Law of Demeter is a heuristic, not a law: pure data pipelines are a deliberate exception; it targets reaching through a stranger to depend on or mutate its internals.
- Coupling and cohesion trade off: splitting a module to "loosen coupling" can shred its cohesion; grade both before cutting.
Example
SEAM a billing function reaches into an Order's private `total` field
GRADE content coupling (reaches internals) + connascence of meaning across a boundary
FIX Order exposes a neutral `amountDue()` value (rule of degree → data coupling);
billing reads the value: agreement is now named, local, and weak
Progressive Disclosure
- Read references/connascence.md - Load when classifying a coupling (static/dynamic forms, strength/locality/degree, the two rules)
- Read references/coupling-ladder.md - Load when grading or improving a seam by the content→data ladder
- Read references/cohesion-ladder.md - Load when judging whether a module's parts belong together, or spotting temporal cohesion
- Read references/law-of-demeter.md - Load when a call site reaches through returned objects (train wrecks)
What ships with it
8 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.
- 1mo ago First seen · 40 lines · 111 tokens per session scan A 4d0e5292651f
connascence-guide is a skill published in the GitHub repository xonovex/platform (6 stars, last pushed 4d ago), licensed MIT. It adds 111 tokens to every session and 727 once invoked, about $0.0004 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 2026-09-08.
Other skills, from other repositories
gh-cli-github
List/create PRs, issues, releases, and CI run status via the gh CLI.
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
review
Adversarial fresh-context review and risk check of an increment before it ships; every finding cites path:line and is re-verified. Use for "review", "qa", "quality check", "critique this".
tech-debt-ci-review
Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.
software-design
This skill should be used when the user asks to "handle errors", "inject dependencies", "return Result", "make it immutable", or implements business logic or error handling.
coding-review-agent-loop
This skill lets you run the coding-review-agent-loop orchestration directly inside an interactive Claude Code session, without calling claude -p for Claude turns.