diagram

A command for creating or updating ASCII diagrams by scanning the code that actually exists in a project. It can map system architecture, API routes, database structures, and deployment infrastructure.

In plain words
What is it for?
Use it to generate architecture, API, database, infrastructure, or all supported diagram types in project documentation.
Why use it?
It keeps technical diagrams tied to the current codebase instead of relying on outdated documentation or hand-drawn assumptions.

Command for Claude Code

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 commands/dr-code/tessera/diagram
Clone the repo
git clone --depth 1 https://github.com/dr-code/tessera

Made for: Claude Code.

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,744 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 $0.00017 $0.02744
Opus 5 $0.00009 $0.01372
Sonnet 5 $0.00003 $0.00549
Haiku 4.5 $0.00002 $0.00274

Measured yesterday against content hash 190b62d9d3a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diagram 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.

.claude/commands/diagram.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Diagram

Scan the actual project and generate/update diagrams based on what exists in code.

Type: $ARGUMENTS

Available types:

  • architecture — System overview: services, connections, data flow → updates docs/ARCHITECTURE.md
  • api — API routes map: all endpoints grouped by resource → updates docs/ARCHITECTURE.md
  • database — Database schema: collections, indexes, relationships → updates docs/ARCHITECTURE.md
  • infrastructure — Deployment topology: servers, containers, regions → updates docs/INFRASTRUCTURE.md
  • all — Generate all diagram types

If --update is passed, replace existing diagrams in-place. Otherwise, show the diagram and ask before writing.

Diagram Format

ALL diagrams use ASCII box-drawing characters. No Mermaid, no SVG, no external tools. ASCII works in every terminal, every markdown renderer, every code review.

Box characters: ┌ ┐ └ ┘ │ ─ ├ ┤ ┬ ┴ ┼
Arrows: → ← ↑ ↓ ──> <── ───>

Type: architecture

Scan the project and generate a system overview diagram.

What to scan:

  1. src/ directory structure — identify services, handlers, adapters

    find src/ -name "*.ts" -o -name "*.tsx" 2>/dev/null | head -50
    
  2. Entry points — find all server/app files

    grep -rl "app.listen\|createServer\|express()\|fastify()\|Hono()" src/ 2>/dev/null
    
  3. Route definitions — find where endpoints are defined

    grep -rn "app\.\(get\|post\|put\|delete\|patch\)\|router\.\(get\|post\|put\|delete\|patch\)" src/ 2>/dev/null
    
  4. Database usage — find which services access the database

    grep -rl "queryOne\|queryMany\|insertOne\|updateOne\|bulkOps\|batch\|StrictDB\|MongoClient\|PrismaClient" src/ 2>/dev/null
    
  5. External service calls — find adapters and API calls

    grep -rl "fetch(\|axios\|got(" src/ 2>/dev/null
    
  6. Package.json — check for framework indicators

    • next → Next.js app
    • express → Express API
    • fastify → Fastify API
    • hono → Hono API

Read the full file on GitHub · 302 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 · 302 lines · 17 tokens per session scan A 190b62d9d3a4

Subscribe to this mod's changes

diagram is a command published in the GitHub repository dr-code/tessera (1 stars, last pushed 21d ago), licensed MIT. It adds 17 tokens to every session and 2,744 once invoked, about $0.0001 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.