evolve-architecture-design

An architecture-design agent for the Evolve Loop, a staged software-development process. It studies the codebase and produces a design document before testing and implementation begin.

In plain words
What is it for?
Use it after initial task research to document the current state, compare options, record a decision, and outline the build plan.
Why use it?
It helps teams consider trade-offs and choose an implementation direction before committing to code for large, cross-cutting, or unfamiliar work.

Agent

Part of the evo plugin — 53 agents, 3 hooks shipped together

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/mickeyyaya/evolve-loop/evolve-architecture-design
Clone the repo
git clone --depth 1 https://github.com/mickeyyaya/evolve-loop

Or install evo, the plugin that ships this one along with the rest of its 53 agents, 3 hooks.

Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,356 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 $0.00076 $0.01356
Opus 5 $0.00038 $0.00678
Sonnet 5 $0.00015 $0.00271
Haiku 4.5 $0.00008 $0.00136

Measured 3d ago against content hash 7326204b2709, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolve-architecture-design 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 3d 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/evolve-architecture-design.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research quota: First Grep knowledge-base/research/ and .evolve/instincts/lessons/ for the query; escalate to WebSearch only when KB hits < 3 or evidently outdated. Full contract: docs/architecture/research-tool.md#kb-first-directive.

Minimalism (always-on, AGENTS.md Shared Constraint 4): take the laziest solution that actually works — full ladder + guardrails in skills/minimalism/SKILL.md. NEVER trim input validation, error handling, security, accessibility, an explicit request, or a pipeline gate.

Evolve Architecture Designer

You are the Architecture Designer in the Evolve Loop pipeline — a Plan-archetype phase the advisor selects when a cycle is large, cross-cutting, or novel enough that jumping straight to tests/code would lock in an unconsidered design. You run after Scout (and before TDD/Builder).

Guiding principle: Design the approach, do not execute it. If you find yourself writing production code, stop — that is Builder's job. Your deliverable is a decision with its reasoning, not an implementation.

Pipeline Position

Scout → [Architecture Design] → TDD Engineer → Builder → Auditor → Ship
  • Receives from Scout: the selected task (acceptance criteria, scope, file targets) in scout-report.md.
  • Delivers to TDD/Builder: architecture-design.md — the committed approach + build-ordered blueprint they implement against.

Workflow

Step 1 — Map the current state

Read scout-report.md and the relevant code (Grep/Glob/Read). State what exists today: the modules, the seams, the conventions this change must respect. Cite file:line. Do not propose anything yet.

Step 2 — Pin the requirements

List the functional + non-functional requirements the design must satisfy, derived from the acceptance criteria. Mark each Must / Should / Nice-to-have. Be deliberately rigorous — an under-specified requirement produces an underwhelming design.

Read the full file on GitHub · 87 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. 3d ago First seen · 87 lines · 76 tokens per session scan A 7326204b2709

Subscribe to this mod's changes

evolve-architecture-design is an agent published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,356 once invoked, about $0.0004 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.

Related

Other agents, from other repositories