architect-design

architect-design is a skill for Claude Code from yugasun/aiops. It costs 58 tokens per session (1,567 once invoked), scanned A, original, Apache-2.0.

A structured design process for turning requirements and domain knowledge into design notes, a technical specification, and updated architecture documents. It uses terms such as modules and interfaces to describe how the system is organized.

In plain words
What is it for?
Use it to gather constraints, identify modules, design interfaces, compare alternatives, record decisions, and prepare NOTES.md and tech-spec.md.
Why use it?
It makes design constraints, alternatives, connections between parts, and risks explicit before implementation begins.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the aiops plugin — 23 skills shipped together

Good fit Use it to gather constraints, identify modules, design interfaces, compare alternatives, record decisions, and prepare NOTES.md and tech-spec.md.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yugasun/aiops/architect-design
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.

Any agent
npx skills add yugasun/aiops --skill architect-design
Clone the repo
git clone --depth 1 https://github.com/yugasun/aiops

Made for: Claude Code.

Or install aiops, the plugin that ships this one along with the rest of its 23 skills.

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.

agentmods badge for architect-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/yugasun/aiops/architect-design.svg)](https://agentmods.dev/skills/yugasun/aiops/architect-design)
Your own site
<a href="https://agentmods.dev/skills/yugasun/aiops/architect-design"><img src="https://agentmods.dev/badge/skills/yugasun/aiops/architect-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,567 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.01567
Opus 5 $0.00029 $0.00783
Sonnet 5 $0.00012 $0.00313
Haiku 4.5 $0.00006 $0.00157

Measured 8d ago against content hash a00ba856d268, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

architect-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 8d 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.

skills/architect-design/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect Design

Structured design process: from grill/domain-modeling conclusions to complete NOTES.md + tech-spec.md + any needed domain documentation updates.

Vocabulary

Use design-vocabulary.md throughout — module, interface, depth, seam, deletion test, leverage, locality. Do not drift into "component," "service," "API," or "boundary."

Inputs

  • Grill conclusions (assumptions exposed, constraints identified)
  • CONTEXT.md domain glossary (from /aiops-setup)
  • docs/adr/ existing architecture decision records
  • .scratch/<feature>/VERDICT.md (if prototyper ran)
  • graphify-out/graph.json (if /code-graph has been run — query via /code-graph query god-nodes, /code-graph query communities for overview)

Process

Step 1: Constraint gathering

Extract constraints from all inputs. Classify:

  • Hard constraints: cannot be violated (existing ADRs, platform limits, team capacity, compliance)
  • Soft constraints: preferences that can be traded off (performance targets, code style, library preferences)

List constraints explicitly in NOTES.md Context section. Reference ADRs by number — do not re-litigate settled decisions unless friction is real enough to warrant revisiting (mark clearly).

Step 1.5: Graph validation (if code graph available)

If graphify-out/graph.json exists, validate constraints against the actual code structure:

  1. Query /code-graph query modules to get the current module inventory
  2. For each constraint referencing existing modules, verify the module exists and matches the constraint's assumptions
  3. Query /code-graph query deps <module> to check dependency claims
  4. Flag any constraint that contradicts the graph (e.g., "Module A doesn't depend on Module B" but the graph shows it does)

Record graph-validated constraints in NOTES.md with [graph-verified] tags.

Step 2: Module identification

Identify the modules needed to satisfy the requirements. For each candidate module:

Read the full file on GitHub · 139 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 8d ago First seen · 139 lines · 58 tokens per session scan A a00ba856d268

Subscribe to this mod's changes

architect-design is a skill published in the GitHub repository yugasun/aiops (4 stars, last pushed 19d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,567 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.