d2

A tool for creating diagrams from text using D2, a diagram language that automatically arranges connected boxes and groups. It is suited to clean diagrams with nested sections.

In plain words
What is it for?
Use it for architecture, infrastructure, network, and deployment diagrams, especially when components need to be grouped inside larger containers.
Why use it?
It removes much of the manual positioning work involved in drawing architecture, network, and deployment diagrams.

Skill for Claude CodeCodex

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 skills/zate/cc-plugins/d2
Any agent
npx skills add Zate/cc-plugins --skill d2
Clone the repo
git clone --depth 1 https://github.com/Zate/cc-plugins

Made for: Claude Code, Codex.

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,400 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00061 $0.01400
Opus 5 $0.00030 $0.00700
Sonnet 5 $0.00012 $0.00280
Haiku 4.5 $0.00006 $0.00140

Measured yesterday against content hash b9997d2c2881, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

d2 scanned grade C with 2 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 yesterday.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://d2lang.com/install.sh | sh -s --

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://d2lang.com/install.sh | sh -s --
plugins/diagrams/skills/d2/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

D2 Diagram Skill

Generate diagrams using D2's declarative syntax. D2 produces clean, modern-looking diagrams with excellent auto-layout, nested containers, and multiple layout engines.

When to use D2:

  • Architecture diagrams with nested components (D2's container nesting is excellent)
  • Clean, modern aesthetic without manual positioning
  • User has d2 installed or prefers it
  • Network/infrastructure diagrams
  • Deployment diagrams with hierarchical grouping

When another format is better:

  • Maximum visual customization (SVG)
  • Diagrams in GitHub/GitLab markdown (Mermaid -- D2 doesn't render natively)
  • Whiteboard/sketch aesthetic (Excalidraw)
  • ER diagrams, Gantt charts (Mermaid has better support)

Consult the design-system skill for color, composition, and quality rules.

Syntax Quick Reference

Basic Connections

server -> database: query
database -> server: results
client -> server: HTTPS

Arrow types:

  • -> directed (default)
  • <-> bidirectional
  • -- undirected

Shapes and Labels

# Named with label
api: API Gateway

# Shapes
db: Database {
  shape: cylinder
}
user: User {
  shape: person
}
decision: Route? {
  shape: diamond
}
queue: Messages {
  shape: queue
}

Available shapes: rectangle (default), square, page, parallelogram, document, cylinder, queue, package, step, callout, stored_data, person, diamond, oval, circle, hexagon, cloud.

Containers (Nested)

D2's killer feature -- nested containers for hierarchy:

aws: AWS {
  vpc: VPC {
    public: Public Subnet {
      alb: Load Balancer {
        shape: hexagon
      }
    }
    private: Private Subnet {
      app: App Server
      db: Database {
        shape: cylinder
      }
      app -> db: SQL
    }
    public.alb -> private.app: HTTP
  }
}

Sequence Diagrams

shape: sequence_diagram

client: Client
server: Server
db: Database

client -> server: POST /users
server -> db: INSERT INTO users
db -> server: OK
server -> client: 201 Created

Read the full file on GitHub · 237 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 237 lines · 61 tokens per session scan C b9997d2c2881

Subscribe to this mod's changes

d2 is a skill published in the GitHub repository Zate/cc-plugins (10 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 1,400 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens