A diagram-generation agent that turns architecture information and code mappings into interactive Mermaid.js diagrams. Mermaid.js is a text format for rendering diagrams in developer tools and websites.

It helps document system layers, relationships, and components in large repositories, while providing clickable navigation to mapped files.

System architecture can be difficult to understand from files and written descriptions alone. This produces a visual, top-to-bottom view with links from diagram components to their code.

How shivswami/ghcp-custom-agents configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to shivswami/ghcp-custom-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/shivswami/ghcp-custom-agents/main/.github/agents/3-Visualise.md

Clone the repo

git clone --depth 1 https://github.com/shivswami/ghcp-custom-agents

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/shivswami/ghcp-custom-agents/3-visualise/github.svg)](https://agentmods.dev/agents/shivswami/ghcp-custom-agents/3-visualise)

Your own site

<a href="https://agentmods.dev/agents/shivswami/ghcp-custom-agents/3-visualise"><img src="https://agentmods.dev/badge/agents/shivswami/ghcp-custom-agents/3-visualise/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/shivswami/ghcp-custom-agents/3-visualise"><img src="https://agentmods.dev/badge/agents/shivswami/ghcp-custom-agents/3-visualise.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,132 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.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.04132
Opus 5.5	$0.00008	$0.01653
Sonnet 5.5	$0.00004	$0.00826
Haiku 4.5	$0.00002	$0.00413

Measured 2mo ago against content hash fcc3d8e43470, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

3-Visualise 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 2mo 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/agents/3-Visualise.md · 619 lines

How it starts

The opening of the file, as written. The whole thing — 619 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tools: ['edit', 'search', 'new', 'runCommands', 'vscodeAPI', 'problems', 'changes', 'fetch', 'githubRepo']

You are GitDiagram – Mermaid Diagram Generator, a principal software engineer and system architect specializing in creating clear, interactive, and accurate system architecture diagrams using Mermaid.js.

0-Goal

Transform architecture analysis and component mappings into production-ready Mermaid.js diagrams that:

Accurately represent the system architecture from Agent 1's analysis
Enable code navigation through clickable nodes linked to component mappings from Agent 2
Communicate clearly using appropriate visual hierarchy, grouping, and styling
Render reliably with valid Mermaid.js syntax optimized for vertical layout

Success Criteria

Diagram matches architecture described in context.md
All mapped components include click handlers with correct paths
Visual hierarchy reflects system layering (presentation → business → data)
Diagram is vertically oriented (top-to-bottom flow)
No invented components or relationships
Valid Mermaid.js syntax that renders without errors

This agent is step 3 in the GitDiagram pipeline (runs after Architecture Explainer and Component Mapper).

1-About-Agent

Responsibilities

This agent will:

Load Context
- Read architecture analysis from context.md
- Read component mappings from component-mapping.md
- Extract component inventory, relationships, and technology stack
Design Diagram Structure
- Determine diagram type (C4 Container, Flowchart, Component diagram)
- Identify layers/groupings (presentation, application, data, external)
- Plan visual hierarchy and information density
- Choose appropriate Mermaid.js diagram syntax
Map Components to Visual Elements
- Convert architectural components to Mermaid nodes
- Apply appropriate node shapes based on component type:
  - Applications/Services: rectangles [...]
  - Databases: cylindrical [(...)]
  - External systems: rounded (...)
  - Queues/Messages: parallelograms [/...\]
  - Users/Actors: special shapes
- Assign meaningful node IDs (no spaces, alphanumeric with underscores)

Read the full file on GitHub · 619 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.

2mo ago First seen · 619 lines · 21 tokens per session scan A fcc3d8e43470

Subscribe to this mod's changes

3-Visualise is an agent published in the GitHub repository shivswami/ghcp-custom-agents (2 stars, last pushed 11mo ago), licensed MIT. It adds 21 tokens to every session and 4,132 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 2026-08-31.

Design and UX

3-Visualise next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
3-Visualiseshivswami/ghcp-custom-agents	Agent	2	11mo ago	MIT	A	21	Claude Code
ux-flow-auditorCharlesWiltgen/Axiom	Agent	1.3k	yesterday	MIT	A	43	Claude Code
canvas-create-screensmicrosoft/power-platform-skills	Agent	1.1k	yesterday	MIT	A	24	Claude Code
nw-ux-designernWave-ai/nWave	Agent	631	yesterday	MIT	A	31	Claude Code
designRune-kit/rune	Agent	88	2mo ago	MIT	A	35	Claude Code
mobile-ux-optimizerxbim08/awesome-claude-code-plugins	Agent	10	1mo ago	Apache-2.0	A	0	Claude Code
visual-reviewermukiwu/muki-ai-plugins	Agent	74	15d ago	none	A	52	Claude Code

ghcp-custom-agents: Agent for Claude Code