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.
npx agentmods add skills/tslateman/duet/excalidrawnpx skills add tslateman/duet --skill excalidrawgit clone --depth 1 https://github.com/tslateman/duetWrote 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.
[](https://agentmods.dev/skills/tslateman/duet/excalidraw)<a href="https://agentmods.dev/skills/tslateman/duet/excalidraw"><img src="https://agentmods.dev/badge/skills/tslateman/duet/excalidraw.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00053 | $0.03374 |
| Opus 5 | $0.00026 | $0.01687 |
| Sonnet 5 | $0.00011 | $0.00675 |
| Haiku 4.5 | $0.00005 | $0.00337 |
Grade A, and why
excalidraw 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Excalidraw Diagram Generator
Generate Excalidraw diagrams programmatically using Python. Produces professional-looking, editable .excalidraw files instead of ASCII art.
Output format: editable .excalidraw JSON files, not ASCII art. See Viewing the Output to open them and Exporting to PNG to render images.
Token cost note: Excalidraw JSON is verbose (4,000-22,000+ tokens per file). Delegate diagram generation to subagents when context is tight.
Quick Start
Method 1: Direct Python Script (Recommended)
Write a Python script using the generator library and run it:
#!/usr/bin/env python3
import sys, os
sys.path.insert(0, os.path.expanduser("~/.claude/plugins/duet/skills/excalidraw/scripts"))
from excalidraw_generator import Diagram, Flowchart, ArchitectureDiagram
# Create your diagram
d = Diagram()
box1 = d.box(100, 100, "Step 1", color="blue")
box2 = d.box(300, 100, "Step 2", color="green")
d.arrow_between(box1, box2, "next")
d.save("my_diagram.excalidraw")
Run with:
python3 /path/to/your_script.py
Method 2: Inline Python Execution
python3 -c "
import sys, os
sys.path.insert(0, os.path.expanduser('~/.claude/plugins/duet/skills/excalidraw/scripts'))
from excalidraw_generator import Diagram
d = Diagram()
a = d.box(100, 100, 'Hello', color='blue')
b = d.box(300, 100, 'World', color='green')
d.arrow_between(a, b)
d.save('hello.excalidraw')
print('Created: hello.excalidraw')
"
API Reference
Diagram Class
The base class for all diagrams.
from excalidraw_generator import Diagram
d = Diagram(background="#ffffff") # white background
Methods
box(x, y, label, width=150, height=60, color="blue", shape="rectangle", font_size=18)
Create a labeled shape. Returns an Element for connecting.
x, y: Position (top-left corner)label: Text to displaycolor: "blue", "green", "red", "yellow", "orange", "violet", "cyan", "teal", "gray", "black"shape: "rectangle", "ellipse", "diamond"
What ships with it
5 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.
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.
- 5d ago First seen · 404 lines · 53 tokens per session scan A d834ae0723b9
excalidraw is a skill published in the GitHub repository tslateman/duet (1 stars, last pushed 8d ago), licensed MIT. It adds 53 tokens to every session and 3,374 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.
Other skills, from other repositories
roadmap-to-workflow
Fan an approved .task/roadmap/ .md out to a dynamic Workflow — parallel planning, serialized implementation, dependency-ordered waves.
to-plan
Capture the chat into .task/task/ .md with ## Description plus ## Plan (Goal/Touches/Logic) — the deepest one-task capture.
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.
to-roadmap
Capture a multi-task initiative into .task/roadmap/ .md — a phase-grouped backlog of ready-to-pick-up items.
to-task
Capture the chat (or a roadmap item) into .task/task/ .md — ## Description only, no ## Plan.
to-spec
Capture load-bearing technical decisions into a standalone .task/spec/ .md — Decision/Rationale/Constrains sections cited via Spec:.