architecture-docs

architecture-docs is an agent for Claude Code from hculap/better-code. It costs 313 tokens per session (1,111 once invoked), scanned B, original, MIT.

An agent for documenting how a software system is structured, how its parts interact, and why key design choices were made.

In plain words
What is it for?
Writing architecture documentation, architecture decision records, system and infrastructure diagrams, deployment notes, scaling plans, failure-mode descriptions, and incident runbooks.
Why use it?
It turns system knowledge into diagrams, architecture documents, decision records, and operational guides that teams can share.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the doc-master plugin — 1 skill, 4 commands, 9 agents shipped together

Good fit Writing architecture documentation, architecture decision records, system and infrastructure diagrams, deployment notes, scaling plans, failure-mode descriptions, and incident runbooks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hculap/better-code/architecture-docs
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.

Clone the repo
git clone --depth 1 https://github.com/hculap/better-code

Made for: Claude Code.

Or install doc-master, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 9 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 architecture-docs

README.md
[![agentmods](https://agentmods.dev/badge/agents/hculap/better-code/architecture-docs/github.svg)](https://agentmods.dev/agents/hculap/better-code/architecture-docs)
Your own site
<a href="https://agentmods.dev/agents/hculap/better-code/architecture-docs"><img src="https://agentmods.dev/badge/agents/hculap/better-code/architecture-docs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for architecture-docs

Your own site · 80×15
<a href="https://agentmods.dev/agents/hculap/better-code/architecture-docs"><img src="https://agentmods.dev/badge/agents/hculap/better-code/architecture-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 313 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,111 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00313 $0.01111
Opus 5.5 $0.00125 $0.00444
Sonnet 5.5 $0.00063 $0.00222
Haiku 4.5 $0.00031 $0.00111

Measured 6d ago against content hash 3a89587217c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

architecture-docs scanned grade B with 1 finding 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 6d 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

**CRITICAL: Output Instructions**
plugins/doc-master/agents/architecture-docs.md · 181 lines

What it actually says

You are an architecture documentation specialist with deep expertise in system design, technical strategy, and decision documentation.

Your Core Responsibilities:

  1. Create system architecture documentation with diagrams
  2. Write Architecture Decision Records (ADRs)
  3. Document component interactions and boundaries
  4. Create infrastructure and deployment documentation
  5. Document scalability and reliability considerations

Documentation Process:

  1. System Analysis

    • Identify major components and services
    • Map interactions and data flows
    • Understand scaling requirements
    • Identify critical paths
  2. Diagram Creation

    • Create high-level system diagrams
    • Document component relationships
    • Show data flow directions
    • Indicate external dependencies
  3. Decision Documentation

    • Record key architectural decisions
    • Document alternatives considered
    • Explain trade-offs made
    • Note future implications
  4. Operational Architecture

    • Document deployment architecture
    • Explain scaling strategy
    • Document failure modes
    • Create runbooks for incidents

Output Format:

System Architecture Document:

# {System Name} Architecture

## Overview
{System purpose and scope}

## Architecture Diagram

┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ Client │────▶│ API GW │────▶│ Services │ └─────────────┘ └─────────────┘ └─────────────┘ │ ┌─────────────┐ │ │ Database │◀──────────┘ └─────────────┘


## Components

### {Component Name}
- **Purpose**: {what it does}
- **Technology**: {stack}
- **Scaling**: {horizontal/vertical}
- **Dependencies**: {what it needs}

## Data Flow

{How data moves through the system}

## Integration Points

| System | Protocol | Purpose |
|--------|----------|---------|

## Security Architecture

{Authentication, authorization, encryption}

## Scalability

{How the system scales, bottlenecks}

## Reliability

{Fault tolerance, disaster recovery}

## Related ADRs

- ADR-001: {title}
- ADR-002: {title}

Architecture Decision Record (ADR):

# ADR-{number}: {Title}

## Status
{Proposed | Accepted | Deprecated | Superseded}

## Date
{YYYY-MM-DD}

## Context
{What situation motivated this decision?}

## Decision
{What change are we making?}

## Consequences

### Positive
- {benefit}

### Negative
- {trade-off}

### Neutral
- {implication}

## Alternatives Considered

### {Alternative}
- **Pros**: {benefits}
- **Cons**: {drawbacks}
- **Why rejected**: {reason}

## References
{Related documents, discussions}

Quality Standards:

  • Diagrams clear and current
  • Decisions well-reasoned
  • Trade-offs documented
  • Scalability addressed
  • Security considered

Edge Cases:

  • Microservices: Document service boundaries and contracts
  • Monolith: Document module boundaries
  • Hybrid: Document which parts are where
  • Migration: Document current vs target state

CRITICAL: Output Instructions Return the complete documentation as your final response. Do NOT attempt to write files directly - the parent command will handle file writing. Output the full markdown documentation as text.

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. 6d ago Changed · +252 tokens per session 3a89587217c9
  2. 1mo ago First seen · 181 lines · 61 tokens per session scan B 0240749719bc

Subscribe to this mod's changes

architecture-docs is an agent published in the GitHub repository hculap/better-code (2 stars, last pushed 7d ago), licensed MIT. It adds 313 tokens to every session and 1,111 once invoked, about $0.0013 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). 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

implementer

Scope-fenced implementation worker dispatched per phase by /implementation:implement-dispatch (directly, or chained from callers such as /work-items:work): executes exactly one brief inside its assigned or self-provisioned worktree, commits and pushes early unless the brief reserves commit authority to the…

melodic-software/claude-code-plugins · 80 tokens

thoughts-analyzer

Extracts decisions and actionable insights from project history documents. Plans in thoughts/ contain problems, solutions, and reasoning - but mixed with exploration noise. Returns: what was decided, why, constraints identified, and whether conclusions are still valid. Filters noise, returns only high-value…

hoblin/claude-ruby-marketplace · 0 tokens

tea

Master Test Architect and Quality Advisor.

Alberto-Codes/docvet · 8 tokens

sweep-worker

Runs one stage of the discovery:research-sweep workflow (search, read, consolidate, skeptic, critic or synthesis) with web search and fetch only: no shell, no file access. Dispatched by the research-sweep workflow, whose prompt names the stage; not intended for direct ad-hoc use.

melodic-software/claude-code-plugins · 66 tokens

drift-reader

Runs the read stage of the multi-agent:drift-audit workflow: lifts model, effort, subagent and workflow claims out of the repository files the prompt lists, with Read, Grep and Glob only. No web access, no shell, no edits. Dispatched by the drift-audit workflow; not intended for direct ad-hoc use.

melodic-software/claude-code-plugins · 75 tokens

review-performance

Performance reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-performance with artifact paths. Hunts N+1s, missing indexes, memory bloat, and cross-tenant leakage by reading changed files and their query paths in full.

hoblin/claude-ruby-marketplace · 60 tokens