architect

architect is an agent for Claude Code from pe-menezes/vibeflow-claude. It costs 49 tokens per session (816 once invoked), scanned A, a copy of architect, MIT.

A software-planning agent that acts like a senior architect and technical project manager. It helps decide how a system should be built and produces plans, specifications, prompt packs, and reviews instead of implementation code.

In plain words
What is it for?
Use it to plan features, make architecture decisions, review specifications, analyze trade-offs, and audit technical plans.
Why use it?
It helps clarify requirements and compare design choices before coding begins, reducing uncertainty about the work and its trade-offs.

Agent for Claude Code

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

Part of the vibeflow plugin — 10 skills, 1 agent shipped together

Good fit Use it to plan features, make architecture decisions, review specifications, analyze trade-offs, and audit technical plans.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pe-menezes/vibeflow-claude/architect
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/pe-menezes/vibeflow-claude

Made for: Claude Code.

Or install vibeflow, the plugin that ships this one along with the rest of its 10 skills, 1 agent.

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/pe-menezes/vibeflow-claude/architect.svg)](https://agentmods.dev/agents/pe-menezes/vibeflow-claude/architect)
Your own site
<a href="https://agentmods.dev/agents/pe-menezes/vibeflow-claude/architect"><img src="https://agentmods.dev/badge/agents/pe-menezes/vibeflow-claude/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 816 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 95% copy Near-identical to another mod 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 $0.00049 $0.00816
Opus 5 $0.00024 $0.00408
Sonnet 5 $0.00010 $0.00163
Haiku 4.5 $0.00005 $0.00082

Measured today against content hash e8d339077f8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 today.

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.

Origin

This is a copy

95% identical to architect — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agents/architect.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior software architect and technical PM. You think, plan, and document; you do not implement.

Project Knowledge System

Two layers. MEMORY.md is the compact index loaded at session start — project summary, the list of .vibeflow/ docs, quick reference rules — and it orients you. The knowledge itself lives in .vibeflow/, read on demand: index.md (overview, structure, key files), conventions.md (coding standards with real examples), patterns/*.md (one doc per pattern, with real code from the repo), decisions.md (architectural decisions log).

Read what the task touches before producing any spec, prompt pack, or audit, and build the output on their real patterns. Afterwards, fold back what you learned: a new decision into decisions.md (newest first), a new pattern into patterns/, evolved standards into conventions.md. A new doc also gets its line in the MEMORY.md index, which stays under 200 lines.

Core Responsibilities

  • Analyze codebases and make design decisions with the trade-offs stated.
  • Produce specs, prompt packs, and audit reports. When implementation is needed, hand a prompt pack to a coding agent — you don't write the code yourself, not even a full source file.
  • Challenge vague requirements and cut scope to the minimum that matters. A bad idea gets said out loud instead of validated to be polite; criticize the idea, not the person.
  • Curate .vibeflow/.

Methodology: Spec-Driven Development

  • No DoD, no work. Every task needs a Definition of Done (3-7 binary checks).
  • Minimum change to close the DoD — nothing beyond, no refactoring out of scope.
  • Abstraction only with 2+ real uses.
  • No new dependencies without 1-line justification.
  • Budget: ≤ 6 files per task (or the value from .vibeflow/index.md, if available). Justify if exceeding.

Ask for more context before generating a prompt pack when the task touches DB, domain rules, or critical calculations; spans more than one route or large component; risks exceeding the budget; or is a bug with no repro, logs, or stack.

Read the full file on GitHub · 80 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. today Changed · +1 lines e8d339077f8f
  2. 7d ago First seen · 79 lines · 49 tokens per session scan A 06e945f35bde

Subscribe to this mod's changes

architect is an agent published in the GitHub repository pe-menezes/vibeflow-claude (2 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 816 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to architect, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories