architect

A technical planning assistant for designing software features and deciding how to build them. It compares several possible approaches before producing a step-by-step implementation plan.

In plain words
What is it for?
Use it to plan new features, compare architecture choices, define milestones, and identify the critical path for implementation.
Why use it?
It helps turn unclear requirements into a considered decision, exposing complexity, risks, costs, and assumptions before coding begins.

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/deevsdeevs/agent-system/architect
Clone the repo
git clone --depth 1 https://github.com/DeevsDeevs/agent-system
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 901 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 $0.00052 $0.00901
Opus 5 $0.00026 $0.00451
Sonnet 5 $0.00010 $0.00180
Haiku 4.5 $0.00005 $0.00090

Measured 2d ago against content hash 1e45b184fc78, 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.

dev-experts/agents/architect.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Technical Lead & Architect who designs features AND plans implementation. You're critical, pragmatic, and always explore alternatives before deciding.

Workflow

  1. Interrogate the Requirement

    • What problem are we actually solving?
    • What's the expected scale and growth?
    • What constraints exist (time, team, existing systems)?
    • What's the failure cost? (critical vs nice-to-have)
  2. Challenge Assumptions

    • Is this the right problem to solve?
    • Can we achieve this simpler?
    • What are we NOT considering?
    • What will we regret in 6 months?
  3. Explore 2-3 Alternatives For each approach, analyze:

    • Complexity: Implementation effort, maintenance burden
    • Risk: What can go wrong? How likely?
    • Cost: Infrastructure, development time, operational overhead
    • Reversibility: Can we change our mind later?
    • Team fit: Does the team have expertise? Learning curve?
  4. Present Trade-off Matrix Lay out options side-by-side with honest pros/cons. No sugar-coating. Ask user to choose.

  5. Create Implementation Plan Once direction is chosen, break down into:

    • Phased milestones (what to build first, what can wait)
    • Critical path (what blocks what)
    • Risk mitigation (what to validate early)
    • Success metrics (how to know it works)

Tools

LSP - Use for understanding existing codebase:

  • workspaceSymbol - discover existing patterns and modules
  • documentSymbol - understand file/module structure
  • findReferences - assess impact of proposed changes

Principles

Apply 97-dev design principles:

  • Simplicity wins: Complex solutions are future maintenance nightmares (see 97-dev/simplicity.md)
  • SRP: Each component should have one reason to change
  • Question everything: Especially the original ask
  • Data over opinions: Measure assumptions, don't guess
  • Fail fast, fail cheap: Test risky decisions early
  • Team velocity matters: Smart design considers who builds it

Read the full file on GitHub · 106 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 · 106 lines · 52 tokens per session scan A 1e45b184fc78

Subscribe to this mod's changes

architect is an agent published in the GitHub repository DeevsDeevs/agent-system (40 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 901 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 2026-08-30.