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 znlgis/my-opencode-deepseek-config --skill codebase-designgit clone --depth 1 https://github.com/znlgis/my-opencode-deepseek-configWrote 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/znlgis/my-opencode-deepseek-config/codebase-design)<a href="https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/codebase-design"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/codebase-design/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/znlgis/my-opencode-deepseek-config/codebase-design"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/codebase-design.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 | $0.00042 | $0.00517 |
| Opus 5.5 | $0.00017 | $0.00207 |
| Sonnet 5.5 | $0.00008 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
codebase-design 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Design
A shared vocabulary for reasoning about code structure. This is a glossary, not a process — use the terms precisely so design discussions stay concrete. Adopt these words over looser ones: say module, not component or service; say interface, not API.
Terms
- Module — a unit of code with a boundary and a purpose. Not "component" or "service"; those imply a specific framework or deployment shape.
- Interface — everything a caller must know to use a module correctly: its functions, its invariants, its error modes, and its performance characteristics. Wider than "API" — it includes the contract a caller relies on.
- Depth — the leverage a module gives per unit of interface. A deep module hides a lot of implementation behind a small interface. A shallow module has a large interface relative to the work it does.
- Seam — a place where you can alter behavior without editing that place (Feathers). A seam is where you insert a test double or swap an implementation.
- Adapter — code that translates one interface to another. One adapter is a hypothetical seam; two adapters make it a real seam worth keeping.
- Leverage — how much downstream code a module's design decision affects. High-leverage decisions (a widely-imported module's interface) deserve the most design care.
- Locality — whether related code lives close together. Poor locality forces readers to jump across the codebase to understand one behavior.
Tests
- Deletion test — delete a module. Does its complexity vanish, or does it reappear scattered across N callers? If the latter, the module was not encapsulating anything real.
- Depth test — is the interface smaller than the implementation it hides? A module whose interface is as big as its body is shallow and probably not earning its place.
Testability
- Accept dependencies; do not create them inside the module.
- Return results; do not produce side effects from a function that claims to compute.
- Keep the surface small — every public entry point is a promise you maintain.
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 · 48 lines · 42 tokens per session scan A 5fcc283f94ed
codebase-design is a skill published in the GitHub repository znlgis/my-opencode-deepseek-config (59 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 517 once invoked, about $0.0002 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
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
archify-review
Review Archify issues, PRs, or code through value, cost, and impact to support evidence-based maintenance decisions. Use for issue triage, change reviews, and code quality assessments.
code-review
Run a final code review on a pull request.
code-breaking-changes
Search for breaking changes in external integration surfaces.
plannotator
Reference for using Plannotator (its plannotator tool when you have one, otherwise the CLI): plan review, code review, annotating files, URLs, folders, and running local apps, annotating the last assistant message, browsing archived plan decisions, exporting or sharing Guided Reviews, and the Plannotator Inbox…
gh-pr-review
Automated Cherry Studio review for local branches, PRs, commits, files, architecture docs, and repository skills. Use for code or documentation reviews that need project-specific naming, main/renderer/shared placement and dependency rules, IpcApi and DataApi boundaries, lifecycle/service ownership, renderer hooks…