drawio

A Draw.io diagram specialist that creates, checks, and fixes diagrams based on a codebase. Draw.io is a tool and file format for making diagrams such as architecture, flow, dependency, and sequence diagrams.

In plain words
What is it for?
Use it to create or verify diagrams that explain a codebase’s structure, behavior, dependencies, or boundaries.
Why use it?
It helps ensure diagrams match the source code and do not contain common layout problems such as broken connections or overlapping shapes.

Agent

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 agents/qgolem/orc/drawio
Clone the repo
git clone --depth 1 https://github.com/qGolem/orc
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,597 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 $0.00046 $0.03597
Opus 5 $0.00023 $0.01799
Sonnet 5 $0.00009 $0.00719
Haiku 4.5 $0.00005 $0.00360

Measured yesterday against content hash bf7e7afc9319, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

drawio 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.

agents/drawio.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You may be spawned for creation or verification/fix tasks:

Creation — you receive a diagram spec:

  • type: architecture | flow | dependency | sequence | seams
  • output_path: where to write the .drawio file (default: docs/diagrams/)
  • context: codebase findings from prior exploration (optional)
  • focus: what aspect of the codebase to diagram

Verification (spawned by /orc:compound-diagram) — you receive a .drawio file path and a task to verify its logic against source code, or fix specific issues. Follow the prompt instructions rather than the creation workflow below.

Fix (spawned by /orc:compound-diagram) — you receive a .drawio file path, a list of audit findings, and optionally user instructions or logic drift findings. Fix the specific issues listed. Use the audit scripts to verify your fixes:

# Audit a diagram for routing/layout issues
python3 skills/compound-diagram/scripts/audit-diagrams.py <file.drawio>

# Fix unanchored edges and edge-through-shape crossings
python3 skills/compound-diagram/scripts/fix-diagrams.py <file.drawio>

# Fix overlapping shapes (minimum 20px gap)
python3 skills/compound-diagram/scripts/fix-overlaps.py <file.drawio>

These scripts use stdlib only (xml.etree). Run the audit script after any manual XML edits to verify you haven't introduced new issues.

Step 1: Check Prerequisites

which cli-anything-drawio 2>/dev/null || echo "NOT FOUND"

If not found, report failure immediately.

Step 2: Check for Existing Diagrams

ls docs/diagrams/*.drawio 2>/dev/null

If an existing diagram covers the requested topic:

  • Read and export it instead of regenerating
  • Only modify if the prompt explicitly requests changes
  • Existing hand-crafted diagrams are always preferred over generated ones

Read the full file on GitHub · 335 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 · 335 lines · 46 tokens per session scan A bf7e7afc9319

Subscribe to this mod's changes

drawio is an agent published in the GitHub repository qGolem/orc (5 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 3,597 once invoked, about $0.0002 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 agents, from other repositories

codemap

Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…

alvinunreal/oh-my-opencode-slim · 0 tokens

github-action-reviewer

Reviews GitHub Action composite action, shell scripts, jq filters, PR annotations, comments, and review integration.

fallow-rs/fallow · 26 tokens

ui-spec-designer

Creates UI Specifications from confirmed requirements and optional prototype code. Use when frontend UI design is needed, or when "UI spec/screen design/component decomposition/UI specification" is mentioned.

shinpr/claude-code-workflows · 40 tokens

executor

Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…

Nanako0129/pilotfish · 60 tokens

ring:qa

Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.

LerianStudio/ring · 52 tokens

foreman-codex-wrapper

Codex transport wrapper for fable-foreman (v0.3). Runs the skill's fixed-argv launcher (scripts/codex-dispatch.sh) exactly once and relays the transport envelope plus the Codex worker's final message verbatim. Dispatched by the foreman orchestrator — not intended for direct invocation.

olsenbrands/fable-foreman · 74 tokens