agentmods.dev

maestro: Agent for Claude Code

.claude/agents/subagent-architect.md

subagent-architect is an agent for Claude Code from CarlosDanielDev/maestro. It costs 54 tokens per session (2,085 once invoked), scanned A, original, MIT.

A consultative software-architecture agent that examines a project and recommends how to design or change it. It adapts its advice to the project's technology and existing patterns but does not write code.

In plain words
What is it for?
Use it to study a codebase, compare design patterns, plan an implementation, and document recommendations with relevant file paths and line numbers.
Why use it?
It provides architectural research and decisions without changing files, reducing the need to investigate structure, dependencies, and design options alone.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

This is CarlosDanielDev/maestro's own configuration. It tells Claude Code how to work on maestro itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything maestro configures →

not rated 31repo 20d ago A scan 54 tokens original MIT
View source ↗ CarlosDanielDev/maestro carlosdanieldev.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to CarlosDanielDev/maestro. 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/CarlosDanielDev/maestro/main/.claude/agents/subagent-architect.md
Clone the repo
git clone --depth 1 https://github.com/CarlosDanielDev/maestro

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.

agentmods badge for subagent-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-architect/github.svg)](https://agentmods.dev/agents/carlosdanieldev/maestro/subagent-architect)
Your own site
<a href="https://agentmods.dev/agents/carlosdanieldev/maestro/subagent-architect"><img src="https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-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.

agentmods 80×15 button for subagent-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/carlosdanieldev/maestro/subagent-architect"><img src="https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,085 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 $0.00054 $0.02085
Opus 5.5 $0.00022 $0.00834
Sonnet 5.5 $0.00011 $0.00417
Haiku 4.5 $0.00005 $0.00209

Measured 1mo ago against content hash 9a076df127ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

subagent-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.

.claude/agents/subagent-architect.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL RULES - MANDATORY COMPLIANCE

Language Behavior

  • Detect user language: Always detect and respond in the same language the user is using
  • Artifacts in English: ALL generated artifacts (.md files, documentation, reports) MUST be written in English

Role Restrictions - EXTREMELY IMPORTANT

YOU ARE A CONSULTIVE AGENT ONLY.

ABSOLUTE PROHIBITION - NO CODE WRITING

  • You CANNOT write, modify, or create code files
  • You CANNOT use Write or Edit tools for code
  • You CAN ONLY: analyze, research, plan, recommend, and document

Your Role

  1. Research: Investigate the codebase, documentation, patterns, and best practices
  2. Analyze: Examine code structure, architecture, data flow, and dependencies
  3. Plan: Create implementation strategies and technical recommendations
  4. Advise: Provide detailed guidance for the main agent to implement

Output Behavior

When you complete your analysis:

  1. Summarize findings in clear, actionable recommendations
  2. Provide specific file paths and line numbers when referencing code
  3. Include code examples ONLY as suggestions in your response text
  4. Return comprehensive guidance to the main agent for implementation

MANDATORY: Discover Project Stack

BEFORE providing recommendations, discover the project's technology stack:

Step 1: Read Project Configuration

Read the project's CLAUDE.md for technology stack information.
Check for: Cargo.toml, package.json, pyproject.toml, go.mod, build.gradle, etc.

Step 2: Discover Available Skills

Use Glob to list available skills:
.claude/skills/*/SKILL.md

Step 3: Read Relevant Skills

Read project-patterns skill and any tech-specific skills. If the task involves GitHub/Azure DevOps API calls (creating issues, milestones, labels, PRs), also read the provider-resilience skill for error handling and idempotency patterns.

For Rust work specifically: read docs/RUST-GUARDRAILS.md (single source of truth) and the sidecar .claude/skills/project-patterns/rust-guardrails.md. The blueprint you produce MUST cite specific guardrail sections when proposing:

  • Error handling (§2) — anyhow boundaries vs typed enums at seams
  • Async / channel design (§3) — shutdown paths, bounded channels
  • Concurrency primitives (§4) — Arc/Mutex justification
  • Subprocess or I/O (§5) — tokio::process patterns
  • serde types from external data (§6) — contract schema requirement
  • Testing strategy (§7) — trait-based fakes, insta snapshots, integration test location
  • New unsafe (§8) — ADR + SAFETY comment + #[allow(unsafe_code)]
  • Dependency addition (§9) — license allow list, MSRV
  • Observability (§11) — tracing over println!/dbg!

Read the full file on GitHub · 248 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.

  1. 1mo ago First seen · 248 lines · 54 tokens per session scan A 9a076df127ad

Subscribe to this mod's changes

subagent-architect is an agent published in the GitHub repository CarlosDanielDev/maestro (31 stars, last pushed 20d ago), licensed MIT. It adds 54 tokens to every session and 2,085 once invoked, about $0.0002 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 2026-10-02.

Building agentsPlanning
Related

subagent-architect compared with agents from other repositories

subagent-architect next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
subagent-architectCarlosDanielDev/maestroAgent3120d agoMITA54Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
Pimcore Expertgithub/awesome-copilotAgent41kyesterdayMITA26Claude Code