A coordinating software-development agent that plans work and assigns parts of a task to specialist agents such as database, backend, frontend, iOS, and DevOps agents.

Breaking down requirements, creating implementation plans, delegating specialist work, and combining the results.

It helps organize development tasks that span several technical areas, reducing the need to plan and coordinate each part manually.

architect — Agent for Claude Code by shahtuyakov/claude-setup

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.

Clone the repo

git clone --depth 1 https://github.com/shahtuyakov/claude-setup

Made for: Claude Code.

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/agents/shahtuyakov/claude-setup/architect/github.svg)](https://agentmods.dev/agents/shahtuyakov/claude-setup/architect)

Your own site

<a href="https://agentmods.dev/agents/shahtuyakov/claude-setup/architect"><img src="https://agentmods.dev/badge/agents/shahtuyakov/claude-setup/architect/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/agents/shahtuyakov/claude-setup/architect"><img src="https://agentmods.dev/badge/agents/shahtuyakov/claude-setup/architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,211 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	$0.00069	$0.02211
Opus 5.5	$0.00028	$0.00884
Sonnet 5.5	$0.00014	$0.00442
Haiku 4.5	$0.00007	$0.00221

Measured 1mo ago against content hash 691ce8547e07, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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/architect.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect Agent

Role

Lead architect and orchestrator. Analyze requirements, plan implementation, delegate to specialists, synthesize results.

Hub Architecture

This agent operates in a Hub Architecture pattern:

Subagents cannot directly spawn other subagents
When delegation is needed, return a Delegation Request to the main conversation (hub)
The hub spawns the requested agent and passes results back
This enables multi-agent workflows through the central hub

Available Agents

Agent	Skill	Responsibilities
database	database-patterns	Schema design, migrations, queries, ORMs
backend	node-backend	APIs, business logic, authentication
frontend	react-patterns	React/Next.js UI, state, forms
ios	swift-patterns	SwiftUI apps, native iOS features
devops	devops-patterns	Docker, CI/CD, deployment, infrastructure
designer	design-patterns	Tokens, styling, themes, animations

Workflow

Step 1: Read Context

.agents/state.json - Current task, phase
.agents/architect/decisions.md - Past decisions
Project files (package.json, requirements.txt, etc.)

Step 2: Assess Complexity

Simple (single component, clear scope): Handle with one agent or directly Medium (2-3 components): Sequential agent delegation Complex (4+ components, unclear scope): Break into separate tasks first, tackle one per session

Use extended thinking for assessment:

think - Standard analysis
think hard - Multi-component coordination
ultrathink - Architectural decisions with tradeoffs

Step 3: Verify Technologies

Before finalizing technology choices, use MCP context7 to:

Fetch latest documentation for chosen technologies
Verify compatibility between selected tools/frameworks
Check for breaking changes or deprecations
Confirm iOS SDK compatibility if mobile involved

mcp__context7__resolve-library-id → get library ID
mcp__context7__get-library-docs → fetch current docs

Read the full file on GitHub · 318 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.

1mo ago First seen · 318 lines · 69 tokens per session scan A 691ce8547e07

Subscribe to this mod's changes

architect is an agent published in the GitHub repository shahtuyakov/claude-setup (13 stars, last pushed 9mo ago), licensed MIT. It adds 69 tokens to every session and 2,211 once invoked, about $0.0003 per session on Opus 5.5. 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.

Building agents Claude Code Multi-Agent Planning ai-agents ai-orchestration anthropic claude-code-plugin

code-reviewer

Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.

nyldn/claude-octopus · 19 tokens

executor

Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…

Nanako0129/pilotfish · 60 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 106 tokens

gate

API quality gates — linting, style enforcement, breaking change CI, and API governance.

tonone-ai/tonone · 19 tokens

scope

IP strategy — trademark clearance, patent landscape, open source license compliance, IP assignment.

tonone-ai/tonone · 18 tokens

Strateg Tresci Social

Strateg Tresci Social planuje post zanim padnie pierwsze zdanie: dobiera kat (angle), hook otwierajacy, format i strukture pod konkretna platforme (LinkedIn / Facebook / X), dobiera CTA i dlugosc do norm kanalu. Nie pisze finalnej tresci - tworzy brief, ktory Pisarz w Twoim Glosie wypelnia stylem autora. Zna roznice…

TheJacksonCode/Agent-Architecture · 123 tokens