architecture-document

architecture-document is a skill for Claude Code from saajunaid/caddis-plugin. It costs 31 tokens per session (2,880 once invoked), scanned A, original, MIT.

A document generator that turns an Architecture.md file into a high-level design or low-level design document. It can produce an editable DOCX file or a presentation-style PPTX summary.

In plain words
What is it for?
Use it to create detailed software architecture documents and concise architecture presentations from an existing Architecture.md.
Why use it?
It removes the need to manually reformat living architecture notes for technical reviews or executive presentations.

Skill for Claude Code

Written for Claude Code: context: fork in frontmatter.

Good fit Use it to create detailed software architecture documents and concise architecture presentations from an existing Architecture.md.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/saajunaid/caddis-plugin/architecture-document
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.

Any agent
npx skills add saajunaid/caddis-plugin --skill architecture-document
Clone the repo
git clone --depth 1 https://github.com/saajunaid/caddis-plugin

Made for: Claude Code.

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-document

README.md
[![agentmods](https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/architecture-document/github.svg)](https://agentmods.dev/skills/saajunaid/caddis-plugin/architecture-document)
Your own site
<a href="https://agentmods.dev/skills/saajunaid/caddis-plugin/architecture-document"><img src="https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/architecture-document/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-document

Your own site · 80×15
<a href="https://agentmods.dev/skills/saajunaid/caddis-plugin/architecture-document"><img src="https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/architecture-document.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,880 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00031 $0.02880
Opus 5.5 $0.00012 $0.01152
Sonnet 5.5 $0.00006 $0.00576
Haiku 4.5 $0.00003 $0.00288

Measured 19d ago against content hash ea66f15a246d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

architecture-document 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 19d 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.

.github/skills/docs/architecture-document/SKILL.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Document Generator

Produce formal High-Level Design (HLD) and Low-Level Design (LLD) documents from the project's living docs/Architecture.md and codebase.

Project Context — Read project-config.md for brand tokens, org name, tech stack, and project metadata used in document headers. Document metadata — Any Markdown companion doc or source doc created or updated in this workflow must follow .github/instructions/document-frontmatter.instructions.md. For DOCX/PPTX deliverables, mirror the same author/date/model fields on the cover page or revision history.

When to Load This Skill

  • Stakeholder requests a formal architecture deliverable
  • Audit or compliance review requires documented HLD/LLD
  • Onboarding pack for new team members
  • Architecture review board submission
  • Project milestone that requires design documentation

Prerequisites

Before generating, ensure:

  1. docs/Architecture.md exists and is current (the @architect agent maintains this)
  2. Architecture diagrams exist in docs/architecture/*.drawio (or .png exports)
  3. project-config.md has a profile set (for org name, tech stack, branding)

Output Formats

Format Skill to Load Best For
DOCX (recommended) .github/skills/document-skills/docx/SKILL.md Full HLD/LLD — editable, ToC, numbered sections
PPTX .github/skills/document-skills/pptx/SKILL.md Executive summary / architecture overview deck
PDF .github/skills/document-skills/pdf/SKILL.md Final read-only distribution (generate from DOCX)

HLD — High-Level Design

Document Structure

COVER PAGE
    Project: <APP_TITLE>
    Organization: <ORG_NAME>
    Document Type: High-Level Design (HLD)
    Version: {from Architecture.md front-matter or git tag}
    Date: {current date}
    Author: {architect or team}
    Status: Draft | Under Review | Approved
    Classification: Internal | Confidential

REVISION HISTORY
    | Version | Date | Author | Changes |

APPROVAL TABLE
    | Role | Name | Signature | Date |

TABLE OF CONTENTS (auto-generated)

§1  INTRODUCTION
    §1.1  Purpose
    §1.2  Scope
    §1.3  Audience
    §1.4  References & Related Documents
    §1.5  Glossary & Abbreviations

§2  EXECUTIVE SUMMARY
    - Business context (1-2 paragraphs)
    - Solution overview (1-2 paragraphs)
    - Key architectural decisions summary

§3  SYSTEM CONTEXT
    §3.1  System Context Diagram (C4 Level 1)
    §3.2  External Systems & Interfaces
    §3.3  User Roles & Access Patterns
    §3.4  Data Sources

§4  ARCHITECTURE OVERVIEW
    §4.1  Architecture Style & Patterns
    §4.2  Component Architecture Diagram (C4 Level 2)
    §4.3  Component Descriptions
          (table: Component | Responsibility | Technology | Interfaces)
    §4.4  Technology Stack Summary

§5  DATA ARCHITECTURE
    §5.1  Data Flow Diagram
    §5.2  Data Sources & Stores
    §5.3  Data Integration Patterns
    §5.4  Data Retention & Archival

§6  INTEGRATION ARCHITECTURE
    §6.1  Integration Patterns (sync/async, push/pull)
    §6.2  API Overview (endpoints, protocols)
    §6.3  External System Interfaces
    §6.4  Message Flows / Event Flows

§7  DEPLOYMENT ARCHITECTURE
    §7.1  Deployment Diagram
    §7.2  Infrastructure Components
    §7.3  Environment Strategy (Dev/UAT/Prod)
    §7.4  Scaling & High Availability

§8  SECURITY ARCHITECTURE
    §8.1  Authentication & Authorization
    §8.2  Data Protection (at rest, in transit)
    §8.3  Network Security
    §8.4  Compliance Requirements

§9  NON-FUNCTIONAL REQUIREMENTS
    §9.1  Performance Targets
    §9.2  Availability & Reliability
    §9.3  Scalability
    §9.4  Maintainability
    §9.5  Observability (logging, monitoring, alerting)

§10  ARCHITECTURAL DECISIONS
    §10.1  Key Decisions Log (ADR summary table)
    §10.2  Alternatives Considered
    §10.3  Constraints & Trade-offs

§11  RISKS & MITIGATIONS
    (table: Risk | Likelihood | Impact | Mitigation)

§12  APPENDICES
    §A  Full Diagram Index
    §B  Glossary
    §C  Referenced Documents

Read the full file on GitHub · 322 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. 19d ago Changed · -7 tokens per session ea66f15a246d
  2. 1mo ago First seen · 322 lines · 38 tokens per session scan A 7dda80b83675

Subscribe to this mod's changes

architecture-document is a skill published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 2,880 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.

Related

Other skills, from other repositories

docx

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…

eigent-ai/eigent · 168 tokens

pptx

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying…

eigent-ai/eigent · 152 tokens

xlsx

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or…

eigent-ai/eigent · 201 tokens

pdf

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…

eigent-ai/eigent · 92 tokens

document-processor

Guidance for processing documents, extracting content, and transforming structured information. Use when the user asks to process, parse, extract, or transform document content such as PDFs, Word files, or spreadsheets.

vixues/LeAgent · 44 tokens

attendance-signin-sheet

A spreadsheet generator for printable attendance or meeting sign-in sheets. It turns a list of names into rows with columns such as signatures, dates, departments, or employee IDs.

vixues/LeAgent · 51 tokens