d2

A guide for writing D2 code, a text-based way to create diagrams that can be exported as SVG images. It covers architecture, flow, sequence, database, class, state, and other diagrams.

In plain words
What is it for?
Use it when creating or reviewing architecture diagrams, flowcharts, API sequences, database relationships, class diagrams, state diagrams, or other D2 files.
Why use it?
It helps choose a suitable diagram structure and write valid D2 code instead of drawing each diagram manually.

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/itsjool/d2-mcp/d2
Any agent
npx skills add ItsJooL/d2-mcp --skill d2
Clone the repo
git clone --depth 1 https://github.com/ItsJooL/d2-mcp

Made for: Claude Code, Codex.

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,064 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 $0.00068 $0.07064
Opus 5 $0.00034 $0.03532
Sonnet 5 $0.00014 $0.01413
Haiku 4.5 $0.00007 $0.00706

Measured yesterday against content hash a6e5588b7d1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

d2 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 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.

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.

skills/d2/SKILL.md · 930 lines

How it starts

The opening of the file, as written. The whole thing — 930 lines — stays where its author put it; the contents beside it link to each section on GitHub.

D2 Diagram Language

D2 is a declarative diagram scripting language that compiles to SVG. Text → diagrams. Docs: https://d2lang.com | Playground: https://play.d2lang.com


Diagram Type Selection

Choose the right diagram type before writing any code:

User wants to show... Use this D2 pattern
System components and how they connect Containers + connections (architecture)
Request/response flow, API interactions, message order shape: sequence_diagram
A process, algorithm, or decision tree Shapes + directed connections (flowchart)
Database tables and foreign keys shape: sql_table (ER diagram)
Class hierarchies, object relationships shape: class (UML class diagram)
System context: users, systems, boundaries (C4) Containers + shape: c4-person + theme 303
A state machine or lifecycle Shapes + labeled connections (state diagram)
Progressive reveal / storytelling steps: {} with animate_interval
Multiple views of the same system layers: {} or scenarios: {}
A dashboard / grid of metrics Container with grid-rows / grid-columns

Default shape: rectangle. Use direction: right or direction: down to control flow.


Workflow: Responding to a Diagram Request

  1. Pick the diagram type (use the table above)

  2. Draft the D2 code — start with core entities, add connections, add style last

  3. Call d2_inspect, then draw an ASCII replica from its output:

    d2_inspect(d2_code=...)
    

    Use the inspect output to hand-draw a clean ASCII diagram using box-drawing characters (┌─┐│└┘├┤┬┴┼ ▶ ◀ ↓ ↑). You are generating this ASCII — not the D2 renderer. This avoids all of D2's known ASCII rendering bugs (cross-container connections, reverse edges, direction:right).

    How to draw it:

    • Containers become labelled boxes: ┌─ Control Plane ──────┐
    • Child shapes are indented inside their parent box
    • Connections are drawn as arrows between boxes with their labels
    • Cross-container connections are shown as arrows spanning between the boxes
    • Use for forward, for reverse, for bidirectional, -- for undirected
    • For sequence diagrams: draw actors as columns with arrows between them
    • For steps/layers: show each board as a separate section

Read the full file on GitHub · 930 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. yesterday First seen · 930 lines · 68 tokens per session scan A a6e5588b7d1c

Subscribe to this mod's changes

d2 is a skill published in the GitHub repository ItsJooL/d2-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 68 tokens to every session and 7,064 once invoked, about $0.0003 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 2026-08-31.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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