What is choose-architecture?

A workflow for choosing and documenting a product’s software stack and overall architecture after its business case is approved. It records major decisions in an architecture document and decision records.

Use it to select verified technology versions, describe the system structure, and document irreversible architecture decisions before writing project rules or code.

It prevents important technical choices from remaining vague or being made before the product requirements are agreed.

How okuzpe/midas-harness configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to okuzpe/midas-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/okuzpe/midas-harness/main/.agents/skills/choose-architecture/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/okuzpe/midas-harness

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/okuzpe/midas-harness/choose-architecture/github.svg)](https://agentmods.dev/skills/okuzpe/midas-harness/choose-architecture)

Your own site

<a href="https://agentmods.dev/skills/okuzpe/midas-harness/choose-architecture"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/choose-architecture/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/okuzpe/midas-harness/choose-architecture"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/choose-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,661 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00055	$0.01661
Opus 5	$0.00028	$0.00830
Sonnet 5	$0.00011	$0.00332
Haiku 4.5	$0.00006	$0.00166

Measured 5d ago against content hash 97f5e465f2ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

choose-architecture 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 5d 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.

.agents/skills/choose-architecture/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

choose-architecture (Phase 4 — Tech & Architecture)

Guard + state: <paths.engine>/templates/skill-state-ritual.md (+ AGENTS.md § Safety / Path resolution). Prompt tool: AskQuestion. On Claude Code, fall back to AskUserQuestion if AskQuestion is not wired. Read paths.state first. Precondition: stage: business_case passed, or tech_architecture in progress. If business case gate has not passed, stop and report missing Phase-3 items.

Turn the signed-off business case into a pinned, verifiable architecture: exact versions, system diagram, ADR per irreversible decision. Orchestrate-tier — Opus reasons; scout does Context7 retrieval.

Does / Does not

Does	Does not
Surface macro forks in plain language; pin + verify versions	Self-advance `stage` or grade its own gate
Write `{product}/architecture.md` + `{product}/adr/ADR-NNN-*.md`	Invent architecture for an unscoped product
Record `phases.tech_architecture.artifacts`, `stage_status: gate_pending`	Bundle macro forks into one stack ADR

When NOT

Business case / go/no-go not signed → /business-plan.
Architecture already frozen and you need rules → /define-conventions.
Stack tweak mid-sprint without a new ADR → stop; open an ADR or defer to tribunal.

Anti-rationalization: pinning versions from memory is a fail — Context7 (or documented web fallback) required before every third-party pin.

Inputs (read first, write last)

paths.state — stage, routing, mcp
{product}/business-plan.md, {product}/idea.md; {product}/market.md optional when track: lite
<paths.engine>/rules/context7-usage.md

Procedure

1. Enumerate requirements + macro-pattern forks

Derive from the business case: functional needs, NFRs implied by success metrics, data/auth/integrations/deployment constraints. Write a checklist so the gate confirms every requirement is covered.

Name 3–5 hardest-to-reverse macro forks (business trade-offs, not jargon):

Read the full file on GitHub · 105 lines

Changes

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.

5d ago Changed · +2 lines 97f5e465f2ab
10d ago First seen · 103 lines · 55 tokens per session scan A f96810f40363

Subscribe to this mod's changes

choose-architecture is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,661 once invoked, about $0.0003 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.

Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

midas-harness: Skill for Claude Code