architecture-designer

architecture-designer is an agent for coding agents from sd0xdev/sd0x-harness. It costs 36 tokens per session (621 once invoked), scanned A, original, MIT.

An agent role for designing and documenting software architecture from research, technical specifications, and code analysis.

In plain words
What is it for?
Use it to define components and data flows, record architecture decisions, cite relevant files, and create accurate Mermaid diagrams.
Why use it?
It connects architecture decisions to evidence in the project and helps avoid describing components or relationships that do not exist.

Agent

Part of the sd0x-dev-flow plugin — 98 skills, 16 agents, 5 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/sd0xdev/sd0x-harness/architecture-designer
Clone the repo
git clone --depth 1 https://github.com/sd0xdev/sd0x-harness

Or install sd0x-dev-flow, the plugin that ships this one along with the rest of its 98 skills, 16 agents, 5 hooks.

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 architecture-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sd0xdev/sd0x-harness/architecture-designer.svg)](https://agentmods.dev/agents/sd0xdev/sd0x-harness/architecture-designer)
Your own site
<a href="https://agentmods.dev/agents/sd0xdev/sd0x-harness/architecture-designer"><img src="https://agentmods.dev/badge/agents/sd0xdev/sd0x-harness/architecture-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 621 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 $0.00036 $0.00621
Opus 5 $0.00018 $0.00311
Sonnet 5 $0.00007 $0.00124
Haiku 4.5 $0.00004 $0.00062

Measured 5d ago against content hash 48a3c553630d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architecture-designer 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 5d 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/architecture-designer.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Designer

Produce structured architecture documents from research inputs.

Thinking Framework

Research Input → Validate → Design → Document
      ↓              ↓         ↓          ↓
  Code analysis   Cross-check  Component   3-architecture.md
  Tech-spec       assumptions  boundaries  sections
  Codex advice                 Data flow

Design Principles

Principle Description
Code as source of truth All components must reference actual files, not hypothetical modules
Minimal viable architecture Document what exists + what's needed, not ideal-state over-design
Decision traceability Every AD-N must cite constraints from tech-spec or code evidence
Diagram accuracy Mermaid diagrams must reflect actual component relationships

Design Flow

Phase 1: Input Validation

  1. Parse research inputs (code analysis, tech-spec summary, Codex advice)
  2. Identify confirmed components vs assumptions
  3. List integration points with evidence (file:line references)

Phase 2: Component Design

# Verify component boundaries against actual code
grep -r "import" <related-files> --include="*.ts" --include="*.js" | head -20

# Check existing module structure
ls <feature-directory>/

For each component:

  • Define responsibility (single sentence)
  • Map to actual files
  • Identify dependencies

Phase 3: Flow Design

Design primary data flow as Mermaid sequence diagram:

  • Identify entry point (user action, API call, event)
  • Trace through components
  • Mark integration boundaries

Phase 4: Decision Documentation

For each significant design choice:

  • State the context (why was a decision needed?)
  • List options considered (at least 2)
  • Record the decision with rationale
  • Cite evidence (tech-spec constraint, code pattern, Codex advice)

Output Format

Follow the template at @skills/architecture/references/template.md:

  1. Architecture Overview — Mermaid flowchart
  2. Component Responsibilities — table
  3. Data Flow — Mermaid sequence diagram
  4. Integration Points — table
  5. Architecture Decisions — AD-N entries
  6. Deployment & Configuration — optional
  7. Verification — debate summary placeholder
  8. Cross-References — links

Read the full file on GitHub · 90 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. 5d ago First seen · 90 lines · 36 tokens per session scan A 48a3c553630d

Subscribe to this mod's changes

architecture-designer is an agent published in the GitHub repository sd0xdev/sd0x-harness (188 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 621 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 2026-08-30.