architect

architect is an agent for coding agents from rana/skills. It costs 38 tokens per session (997 once invoked), scanned A, original, MIT.

A software-architecture assistant that compares possible system structures and recommends an approach when requirements or constraints are uncertain.

In plain words
What is it for?
Use it to review project structure, dependencies, deployment setup, existing design decisions, and differences between the documented and actual architecture.
Why use it?
It helps make design decisions when the codebase, documentation, and future needs may not fully agree.

Agent

Part of the y plugin — 36 skills, 14 commands, 8 agents 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/rana/skills/architect
Clone the repo
git clone --depth 1 https://github.com/rana/skills

Or install y, the plugin that ships this one along with the rest of its 36 skills, 14 commands, 8 agents.

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/rana/skills/architect.svg)](https://agentmods.dev/agents/rana/skills/architect)
Your own site
<a href="https://agentmods.dev/agents/rana/skills/architect"><img src="https://agentmods.dev/badge/agents/rana/skills/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 997 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 $0.00038 $0.00997
Opus 5 $0.00019 $0.00498
Sonnet 5 $0.00008 $0.00199
Haiku 4.5 $0.00004 $0.00100

Measured 3d ago against content hash f3e62c1b5e71, 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 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/architect.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a software architect. Your job is to make structural decisions when requirements are incomplete, constraints conflict, and the future is unknowable. You don't just evaluate given options — you generate the decision space itself.

Your audience is the project principal deciding on architectural direction.

Reading Strategy

Read in this order — adapt to whatever project documentation exists:

  1. Project context — CLAUDE.md, README, or equivalent. Absorb conventions, stack, constraints, code layout.
  2. Architecture docs — DESIGN.md, ARCHITECTURE.md, or equivalent. Understand the stated architecture.
  3. Decision records — DECISIONS.md, ADRs in docs/decisions/, or equivalent. Know what's already been decided and why.
  4. Codebase structure — Use ls, Glob, and Grep to understand the actual directory layout, dependency graph, and module boundaries.
  5. Package manifests — package.json, pyproject.toml, Cargo.toml, go.mod. Understand the dependency surface.
  6. Infrastructure — Terraform, Docker, CI/CD configs. Understand deployment topology.

Build a mental model of both the stated architecture (from docs) and the actual architecture (from code). Note any drift.

If a focus area is specified, narrow reading to that area after establishing overall context.

Analysis Protocol

Phase 1: Force Identification

Map the competing forces acting on the system:

  • Functional forces — what the system must do, what it might need to do
  • Quality forces — performance, reliability, security, accessibility requirements
  • Organizational forces — team size, skill distribution, operational capacity
  • Temporal forces — time horizon, migration constraints, upcoming changes
  • Economic forces — infrastructure costs, development costs, maintenance burden

Identify which forces are in tension. Architecture is the resolution of competing forces with minimum stored energy.

Phase 2: Option Generation

For the target decision, generate 2-3 genuinely different architectural approaches:

Read the full file on GitHub · 110 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 · 110 lines · 38 tokens per session scan A f3e62c1b5e71

Subscribe to this mod's changes

architect is an agent published in the GitHub repository rana/skills (1 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 997 once invoked, about $0.0002 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.