What is the-architect?

A guide for making and recording major software architecture decisions, such as choosing a database, service boundary, or integration design. It keeps human experts responsible for the final decision.

Use it to compare structural options, examine cross-cutting concerns such as authentication or observability, and write an ADR (Architecture Decision Record) that explains the decision.

It prevents important choices from remaining undocumented or being made without comparing costs, constraints, and long-term effects.

the-architect — Skill for Claude Code by jpantsjoha: A guide for making and recording major software architecture…

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/jpantsjoha/ai-native-developer-experience/the-architect

Any agent

npx skills add jpantsjoha/ai-native-developer-experience --skill the-architect

Clone the repo

git clone --depth 1 https://github.com/jpantsjoha/ai-native-developer-experience

Made for: Claude Code.

Or install join-the-team, the plugin that ships this one along with the rest of its 21 skills, 3 commands, 1 hook.

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/jpantsjoha/ai-native-developer-experience/the-architect.svg)](https://agentmods.dev/skills/jpantsjoha/ai-native-developer-experience/the-architect)

Your own site

<a href="https://agentmods.dev/skills/jpantsjoha/ai-native-developer-experience/the-architect"><img src="https://agentmods.dev/badge/skills/jpantsjoha/ai-native-developer-experience/the-architect.svg" alt="Measured on agentmods" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 947 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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 5.1	$0.00041	$0.00947
Opus 5	$0.00020	$0.00474
Sonnet 5	$0.00008	$0.00189
Haiku 4.5	$0.00004	$0.00095

Measured 6d ago against content hash 3dfe8e811a2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

the-architect 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 6d 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/the-architect/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Architect

Keep the architecture ladder human-owned. Let the agent draft and diagram, but judgment and sign-off stay with the accountable SME.

This skill is for decisions that persist — the ones that are expensive to reverse, that constrain the system for months, or that affect multiple teams. Implementation details belong in code review. Architecture decisions belong here.

When to use

Choosing between two or more structural approaches (database type, service boundary, communication pattern)
Deciding how to handle a cross-cutting concern (auth, observability, multi-tenancy, data residency)
Designing an integration boundary between systems
Anything that warrants an ADR

Procedure

State the decision to be made — one sentence. If you cannot state it in one sentence, it is not one decision.
Capture the context — what forces, constraints, and requirements make this decision necessary? What is the status quo, and why is it insufficient?
Enumerate the options — at least two credible options. For each:
- What are the benefits?
- What are the costs and trade-offs?
- What does it require from the surrounding system?
- What is the failure mode?
Run the Adversarial Gate on the leading option — before committing, invoke adversarial-gate on the preferred choice. A clean gate result is a prerequisite for committing to the decision.
State the decision — which option is chosen and why. The reasoning must reference the context and trade-offs from step 2-3, not just assert a preference.
Record consequences — what does this decision make easier? What does it make harder? What does it prevent?

Author the ADR — format:

---
status: draft
id: ADR-NNNN
date: <date>
deciders: [<handle>]
---

# ADR-NNNN: <short title>

## Status
draft | approved | superseded

## Context
<forces, constraints, why a decision is needed>

## Decision
<the chosen option and reasoning>

## Consequences
<what becomes easier, harder, or foreclosed>

A decision's lifecycle is visible in both the filename postfix and the status: field: ADR/ADR-NNNN-<slug>-DRAFT.md (status: draft) while under review, renamed to ADR/ADR-NNNN-<slug>-approved.md (status: approved) on approval.

Read the full file on GitHub · 93 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.

6d ago First seen · 93 lines · 41 tokens per session scan A 3dfe8e811a2d

Subscribe to this mod's changes

the-architect is a skill published in the GitHub repository jpantsjoha/ai-native-developer-experience (11 stars, last pushed 29d ago), licensed Apache-2.0. It adds 41 tokens to every session and 947 once invoked, about $0.0002 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.

Planning Writing and docs agent-skills ai-agents claude-code developer-experience harness-engineering mcp

last30Days

Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…

chaitanyagiri/munder-difflin · 83 tokens

thisWeek

Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…

chaitanyagiri/munder-difflin · 77 tokens

the-architect