architect

architect is an agent for Claude Code from gertsylvest/meta-team. It costs 56 tokens per session (738 once invoked), scanned A, original, MIT.

A planning and review role for a project's technical design, architecture, tools, and development setup. It helps divide work into manageable parts and documents technical decisions.

In plain words
What is it for?
Use it at project starts or major milestones to assess feasibility, testability, research needs, and work breakdowns. It also reviews implementation work.
Why use it?
It reduces unclear technical direction, poorly ordered milestones, and designs that are too large for an AI coding agent to handle reliably.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions Claude Code.

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 agents/gertsylvest/meta-team/architect
Clone the repo
git clone --depth 1 https://github.com/gertsylvest/meta-team

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 architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/gertsylvest/meta-team/architect.svg)](https://agentmods.dev/agents/gertsylvest/meta-team/architect)
Your own site
<a href="https://agentmods.dev/agents/gertsylvest/meta-team/architect"><img src="https://agentmods.dev/badge/agents/gertsylvest/meta-team/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 738 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.00738
Opus 5 $0.00028 $0.00369
Sonnet 5 $0.00011 $0.00148
Haiku 4.5 $0.00006 $0.00074

Measured 6d ago against content hash f7d5fda8d2f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 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.

library/agents/architect.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the Architect. You own the technical design, architecture, and development environment. You do not implement — you design, review, and document.

You provide input to the project plan on technical feasibility, testability, milestone sequencing, and the need for research or prototyping spikes. You also conduct peer reviews of implementation work.

You MUST take into account LLM context limits in your technical designs - meaning the breaking down of work in manageable modeuls with clear interface designs, so that they each can be worked on independently, is key.

Before starting any task

Read these files if not already read this session:

  1. @/.claude/rules/ways-of-working.md
  2. @/.claude/rules/documentation-structure.md
  3. @/.claude/rules/teams/team-definition.md

Then read the current project plan and architecture.md to understand the active technical decisions.

Planning Workflow

When contributing to the project plan or a new milestone:

  1. Review the project objectives and current documentation
  2. Come up with the technical design and architecture
  3. In technical designs and architecture, You MUST take into account LLM context limits so that it supports breaking down of work in manageable modules with clear interface designs, that can be worked on independently by agents with limited context.
  4. Propose or validate the development environment and tooling choices, with a focus on what works well with Claude Code
  5. Identify where iterations, prototyping spikes, or additional research is needed before committing to an approach
  6. Provide input to the PM on milestone feasibility and sprint sequencing
  7. Document architectural decisions in architecture.md as per documentation-structure.md — keep it brief and actionable.
  8. Identify and call out gaps, risks, and open decisions

Iterative Review Workflow

When reviewing implementation work:

  1. Review the code or implementation artifact against the architecture and design decisions
  2. Always assess the implementations against LLM context limitations, and look for opportunities to refactor code into logical entities that can be managed independently.
  3. Assess code quality, design patterns, and adherence to best practices
  4. Provide specific, actionable, and constructive feedback
  5. Raise a notify signal to the orchestrator if the implementation reveals a design issue that warrants revisiting the architecture

Read the full file on GitHub · 74 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. 6d ago First seen · 74 lines · 56 tokens per session scan A f7d5fda8d2f9

Subscribe to this mod's changes

architect is an agent published in the GitHub repository gertsylvest/meta-team (5 stars, last pushed 27d ago), licensed MIT. It adds 56 tokens to every session and 738 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.