Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-confignpx agentmods add skills/anastasiyaw/codex-claude-code-config/architecture-qualityWrote 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/anastasiyaw/codex-claude-code-config/architecture-quality)<a href="https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/architecture-quality"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/architecture-quality/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/anastasiyaw/codex-claude-code-config/architecture-quality"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/architecture-quality.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 | $0.00128 | $0.01383 |
| Opus 5 | $0.00064 | $0.00691 |
| Sonnet 5 | $0.00026 | $0.00277 |
| Haiku 4.5 | $0.00013 | $0.00138 |
Grade A, and why
architecture-quality 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 9d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture quality — readable by construction
This skill turns the architecture decision into a small, repeatable delivery
contract. It complements architecture-first; it does not add layers for their own
sake.
Working contract
Before a non-trivial web or service change, record these five facts in
ARCHITECTURE.md or docs/architecture/README.md:
- Feature/domain modules — name them by reason to change, not by a generic
utils,helpersorservicesbucket. - Ownership — each mutable state, database table boundary and external side effect has one owner.
- Dependency direction — policy/domain code is independent of the web framework, ORM, queue and filesystem; adapters point inward through small ports.
- Vertical slice — prove one user-visible path from entry point to state and test before multiplying layers or pages.
- Verification boundary — list the architecture checks and the test command that must remain green after the change.
If the project is a small script or a single-module experiment, state that scope and skip the document. A missing document is a finding only once the project has enough shape to need one, not a reason to create ceremony around a toy.
Web application shape
- Keep routes/controllers thin: parse input, call a use-case or feature API, map the result and return. Do not put business policy, SQL and provider retries in a route.
- Keep domain/use-case code framework-free where practical. Inject ports for storage, clocks, queues and providers; keep concrete adapters at the edge.
- Organize user-facing behavior by feature or bounded context. A page may compose features, but one feature must not reach into another feature's private state.
- Give each page a stable route-level composition boundary. Shared UI primitives are visual primitives, not a second business-logic layer.
- Treat a
utilsorcommonimport that keeps growing as a boundary question. Move code to the module that owns its reason to change; do not create a universal bag. - Prefer a modular monolith until an independently deployable or scalable boundary is proven. A microservice split is not a substitute for a missing internal boundary.
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.
- 9d ago First seen · 121 lines · 128 tokens per session scan A aa681e98404d
architecture-quality is a skill published in the GitHub repository AnastasiyaW/codex-claude-code-config (149 stars, last pushed today), licensed MIT. It adds 128 tokens to every session and 1,383 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
discount-review
Inspect the discount policy fixture with a repeatable review checklist and helper script.
code-review
Perform comprehensive code reviews focusing on best practices, security vulnerabilities, performance optimization, and maintainability.
code-review
Reviews code for bugs, security issues, and best practices.
calling-llms
Use when sending chat completions through liter-llm and routing to a specific provider via the provider/model prefix. Covers the chat call shape, provider routing, modelhint, message roles, and error categories.
running-the-proxy
Use when running the liter-llm api OpenAI-compatible gateway — virtual keys, per-key rate limits, budgets, cost tracking, and model routing. Covers the TOML config and the 22 REST endpoints.
streaming-responses
Use when streaming tokens incrementally from an LLM via liter-llm over SSE or async iterators. Covers chatstream, delta handling, and null-content chunks.