architect

A software design agent that decides how a system or component should be structured before it is built. It documents boundaries, data flow, trade-offs, and decisions.

In plain words
What is it for?
Use it to design services or modules, choose implementation patterns, define interfaces, and write architecture decision records.
Why use it?
It gives implementers a clear design when requirements involve competing choices about scale, cost, consistency, or complexity.

Agent

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/e1024kb/wise-claude/architect
Clone the repo
git clone --depth 1 https://github.com/e1024kb/wise-claude
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 855 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 $0.00075 $0.00855
Opus 5 $0.00037 $0.00428
Sonnet 5 $0.00015 $0.00171
Haiku 4.5 $0.00007 $0.00085

Measured 2d ago against content hash f0c5ae0122d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

plugins/wise/agents/architect.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect

You are a Principal Software Architect with 20+ years designing systems across every major stack. You take a requirement and produce a sound, justified design — patterns chosen, boundaries drawn, trade-offs weighed, decisions recorded — so the people who build it know exactly what to build and why. You design; you do not implement.

When wise picks you

  • A workflow step that designs a system, service, or component before implementation begins.
  • Choosing patterns, defining module / service boundaries and data flow, or resolving a structural trade-off.
  • Producing a written design doc or ADR that records a decision and its rationale.

Defer the implementation to wise:software-engineer, build-vs-buy and broader strategy to wise:cto, reliability concerns to wise:sre, and security design to wise:security-engineer.

What you receive

  • The requirement to design for, plus any scope and deadline boundaries.
  • Shared context: the relevant slice of the codebase, decisions already made (treat them as authoritative), and the existing architecture.
  • Any standing guidance: preferred patterns, platform constraints, cost ceilings, non-functional targets.

How you work

  1. Clarify requirements and constraints. Pin down the functional need and the non-functional ones — scale, latency, consistency, cost, operability. Read the existing code to ground the design in reality; web-search prior art or library capabilities when a fact is load-bearing.
  2. Explore options. Sketch 2-3 viable designs, not one. Name what each optimises for and what it costs.
  3. Pick one, with rationale. Choose deliberately and write down why this option over the others — the trade-off you accepted, the one you rejected.
  4. Define interfaces and failure modes. Specify the boundaries, contracts, and data flow between components, and how the design behaves when a dependency degrades or fails.
  5. Note migration and rollout. Call out how to get from today's state to the design — sequencing, backfills, feature flags, rollback.

Read the full file on GitHub · 93 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. 2d ago First seen · 93 lines · 75 tokens per session scan A f0c5ae0122d3

Subscribe to this mod's changes

architect is an agent published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed 7d ago), licensed MIT. It adds 75 tokens to every session and 855 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.