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 darellchua2/opencode-config-template --skill clean-architecture-skillgit clone --depth 1 https://github.com/darellchua2/opencode-config-templateWrote 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/darellchua2/opencode-config-template/clean-architecture-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/clean-architecture-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/clean-architecture-skill/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/darellchua2/opencode-config-template/clean-architecture-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/clean-architecture-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 196 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 533 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00030 | $0.00522 |
| Opus 5.5 | $0.00012 | $0.00209 |
| Sonnet 5.5 | $0.00006 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
clean-architecture-skill 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
Structure codebases by vertical feature slices + horizontal layers (domain ← application ← infrastructure ← presentation), enforce the dependency rule (source dependencies point inward only), define contracts at boundaries.
When to use me
- Structuring a new codebase or module; deciding where a piece of code belongs
- Reviewing whether a boundary is real (enforced) or decorative
Canonical house layouts: frontend features/<feature>/{_components,_containers,hooks} + domains/<feature>; backend modules/<module>/{domain,application,infrastructure,presentation} (domain holds interfaces, infrastructure holds implementations).
House Learnings
Learning: doc-claimed-purity-vs-reality
A layer rule documented but violated by >10 call sites is a false contract — leaving doc and code in disagreement trains every developer to ignore both. Either enforce the boundary with tooling (no-restricted-imports per-directory overrides, madge --circular, dependency-cruiser in CI) or rewrite the doc to describe reality. Never let architecture docs and code drift — the drift becomes the de facto standard.
Detection: rg "from '@prisma/client'|from 'pg'" src/domain/ -l | wc -l · npx madge --circular --extensions ts src/domain/
Learning: cross-container-hook-borrowing
A feature container must NEVER import from a sibling container via relative path (../../_containers/ReportDetail/useReportDetail) — invisible coupling that breaks silently on refactor. If two containers need one hook, extract to the feature's hooks/ (intra-feature) or domains/{feature}/hooks/ (cross-feature). Containers import ONLY from @/-aliased shared locations or their own feature's hooks/.
Detection: rg "from\s+['\"](\.\./)+.*_containers" --type ts --type tsx
Removed 2026-09: layered/hexagonal/clean-architecture comparison essays, dependency-rule diagrams, vertical/horizontal boundary walkthroughs, cross-cutting-concern lists, frontend/backend directory deep-dives, steps/common-issues ceremony — textbook architecture knowledge; the two codified learnings are this config's real additions.
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 Changed · -517 lines 9a89b325df60
- 1mo ago First seen · 548 lines · 30 tokens per session scan A be683c16bfea
clean-architecture-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed 28d ago), licensed Apache-2.0. It adds 30 tokens to every session and 522 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 2026-09-03.
Other skills, from other repositories
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…
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
software-code-refactoring
Improve production code quality while preserving all existing test behavior. Commonly used for the Refactor phase of TDD red-green-refactor, but applicable to any codebase with tests. Use when production code works but needs cleanup — reducing duplication, improving naming, simplifying complexity, aligning with…
recipe-add-integration-tests
Add integration/E2E tests to existing codebase using Design Docs.
ring:running-dev-cycle
Running the backend dev cycle: implements every task in a rolling-wave plan.md (ring:writing-plans format) for a Go/TS service, driving specialist agents through Gate 0 implementation/TDD, Gate 8 parallel review, and Gate 9 validation per epic, elaborating later phases at each phase boundary. Use when starting or…
ring:instrumenting-streaming-events
Instrumenting streaming events: wires lib-streaming event emission end-to-end into a Lerian Go service via a 13-gate cycle (catalog, Builder bootstrap, Emit sites, outbox, HTTP manifest, NoopEmitter fallback, integration and chaos tests), dispatching ring:backend-go under TDD. Consumes the validated…