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 ashtonian/llm-init --skill architecture-reviewgit clone --depth 1 https://github.com/ashtonian/llm-initWrote 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/ashtonian/llm-init/architecture-review)<a href="https://agentmods.dev/skills/ashtonian/llm-init/architecture-review"><img src="https://agentmods.dev/badge/skills/ashtonian/llm-init/architecture-review/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/ashtonian/llm-init/architecture-review"><img src="https://agentmods.dev/badge/skills/ashtonian/llm-init/architecture-review.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 | $0.00011 | $0.00835 |
| Opus 5 | $0.00005 | $0.00417 |
| Sonnet 5 | $0.00002 | $0.00167 |
| Haiku 4.5 | $0.00001 | $0.00084 |
Grade A, and why
architecture-review 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 10d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review architecture decisions, assess tradeoffs, and identify edge cases.
Instructions
Perform a comprehensive architecture and design review of the current codebase or a specified feature area.
Phase 1: Inventory Decisions
- Read
docs/spec/.llm/PROGRESS.mdfor documented architecture decisions. - Read relevant specs in
docs/spec/biz/. - Read existing ADRs (
docs/spec/biz/adr-*.md) if any exist. - Scan the codebase for architectural patterns:
- Project structure and module organization
- Dependency injection / configuration patterns
- Data flow and state management
- External integrations and boundaries
- Error handling patterns
- Concurrency and synchronization patterns
- API design patterns
Phase 2: Assess Each Decision
For each architectural decision found, evaluate:
| Criterion | Question |
|---|---|
| Fitness | Does this decision serve the current requirements well? |
| Tradeoffs | What was gained? What was sacrificed? |
| Alternatives | What other approaches could work? Would they be better now? |
| Scalability | How does this decision scale with growth (data, traffic, team size)? |
| Maintainability | How easy is it to change this later? What's the blast radius of a change? |
| Risk | What could go wrong? What's the worst-case scenario? |
| Edge Cases | What boundary conditions exist? Are they handled? |
| Consistency | Is this pattern applied consistently, or are there deviations? |
Phase 3: Identify Issues
Look for:
- Coupling: Components that are too tightly coupled or have circular dependencies
- Missing abstractions: Areas where an interface or abstraction boundary would help
- Inconsistencies: Different patterns used for the same concern
- Over-engineering: Abstractions that add complexity without clear benefit
- Under-engineering: Areas that will break under foreseeable growth
- Security gaps: Auth boundaries, input validation, data exposure
- Performance risks: N+1 queries, unbounded collections, missing indexes, no caching
- Testing gaps: Untested critical paths, missing integration tests
- Operational gaps: Missing health checks, no observability, no graceful shutdown
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.
- 10d ago First seen · 97 lines · 11 tokens per session scan A 852a0a1601b4
architecture-review is a skill published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 7mo ago), licensed MIT. It adds 11 tokens to every session and 835 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…