A planning guide for choosing a software system’s structure and technology stack based on a project’s goals. A technology stack is the set of programming languages, frameworks, databases, and other tools used to build a system.

Use it after analysing a project’s vision to design its architecture and select technologies for each system layer. In workspace mode, it reads and writes the project’s architecture documents in the specified .aha-loop directory.

It gives technical decisions a documented rationale instead of choosing tools ad hoc. It also compares candidate technologies and checks that selected versions are current and stable.

architect — Skill by YougLin-dev

Install

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.

agentmods

npx agentmods add skills/youglin-dev/aha-loop/architect

Any agent

npx skills add YougLin-dev/Aha-Loop --skill architect

Clone the repo

git clone --depth 1 https://github.com/YougLin-dev/Aha-Loop

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,217 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

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	$0.00037	$0.02217
Opus 5	$0.00018	$0.01108
Sonnet 5	$0.00007	$0.00443
Haiku 4.5	$0.00004	$0.00222

Measured 2d ago against content hash 52736e8a95e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architect scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://crates.io/api/v1/crates/tokio" | jq '.crate.max_stable_version'

.agents/skills/architect/SKILL.md · 402 lines

How it starts

The opening of the file, as written. The whole thing — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect Skill

Research, evaluate, and decide on technology stack and system architecture based on project requirements.

Workspace Mode Note

When running in workspace mode, all paths are relative to .aha-loop/ directory:

Vision analysis: .aha-loop/project.vision-analysis.md
Architecture output: .aha-loop/project.architecture.md

The orchestrator will provide the actual paths in the prompt context.

The Job

Read project.vision-analysis.md for requirements
Research candidate technologies for each layer
Evaluate and compare options
Make decisions with documented rationale
Design system architecture
Output project.architecture.md

Core Principles

1. Prefer Latest Stable Versions

Always use the latest stable version of libraries unless there's a specific reason not to.

## Version Selection Process

1. Query official source for latest version:
   - Rust: crates.io API or `cargo search`
   - Node: npmjs.com or `npm view [pkg] version`
   - Python: pypi.org or `pip index versions`

2. Check release date and stability:
   - Released > 2 weeks ago (not bleeding edge)
   - No critical issues in GitHub issues
   - Changelog shows no breaking changes from common patterns

3. Document the version and why:
   - Record in project.architecture.md
   - Add to knowledge/project/decisions.md

2. Consider Long-term Maintenance

Active community and regular updates
Good documentation
Large ecosystem of plugins/extensions
Backed by reputable organization or strong community

3. Evaluate Total Cost

Learning curve for the team/AI
Bundle size / binary size
Runtime performance
Development velocity

Research Process

Step 1: Identify Technology Layers

Based on project type, identify which layers need decisions:

Layer	Examples
Language	Rust, TypeScript, Python, Go
Frontend Framework	React, Vue, Svelte, SolidJS
Backend Framework	Axum, Actix, Express, FastAPI
Database	PostgreSQL, SQLite, MongoDB
ORM/Query Builder	Diesel, SQLx, Prisma, Drizzle
Authentication	JWT, Sessions, OAuth providers
Deployment	Docker, Serverless, VPS
Testing	Built-in, Jest, Pytest, Vitest

Read the full file on GitHub · 402 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.

2d ago First seen · 402 lines · 37 tokens per session scan A 52736e8a95e9

Subscribe to this mod's changes

architect is a skill published in the GitHub repository YougLin-dev/Aha-Loop (181 stars, last pushed 7mo ago), licensed MIT. It adds 37 tokens to every session and 2,217 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Planning

systematic-debugging

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

obra/superpowers · 21 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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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

architect