practice-sysdesign

practice-sysdesign is a command for coding agents from kirilxd/swe-interview-coach. It costs 63 tokens per session (1,304 once invoked), scanned A, original, MIT.

A guided system-design practice session where you describe an application's architecture and an interviewer sketches it live on a drawing canvas.

In plain words
What is it for?
Use it to prepare for system-design interviews by discussing architecture, drawing components, and reviewing which areas you covered.
Why use it?
It gives you a structured way to practise explaining how software systems work, with hints and no score or surprise questions.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the swe-interview-coach plugin — 3 skills, 17 commands, 4 agents shipped together

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/kirilxd/swe-interview-coach/practice-sysdesign
Clone the repo
git clone --depth 1 https://github.com/kirilxd/swe-interview-coach

Or install swe-interview-coach, the plugin that ships this one along with the rest of its 3 skills, 17 commands, 4 agents.

Wrote 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.

agentmods badge for practice-sysdesign

README.md
[![agentmods](https://agentmods.dev/badge/commands/kirilxd/swe-interview-coach/practice-sysdesign.svg)](https://agentmods.dev/commands/kirilxd/swe-interview-coach/practice-sysdesign)
Your own site
<a href="https://agentmods.dev/commands/kirilxd/swe-interview-coach/practice-sysdesign"><img src="https://agentmods.dev/badge/commands/kirilxd/swe-interview-coach/practice-sysdesign.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,304 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 $0.00063 $0.01304
Opus 5 $0.00032 $0.00652
Sonnet 5 $0.00013 $0.00261
Haiku 4.5 $0.00006 $0.00130

Measured 4d ago against content hash f1a02f869b89, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

practice-sysdesign 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 4d 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.

commands/practice-sysdesign.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running /practice-sysdesign.

Step 0 — Boot the canvas

Run bash "${CLAUDE_PLUGIN_ROOT}/scripts/ensure-canvas.sh" and parse its LAST line:

  • READY → set canvas_mode = true. The script has already opened http://localhost:9999 in the user's browser.
  • Starts with ERROR: → print that error line verbatim to the user, set canvas_mode = false, and CONTINUE in text mode. Never abort coaching over canvas trouble.

(The SWE_INTERVIEW_COACH_CONFIG_DIR/_PORT env vars are test-only knobs; this command's contract is the default path ~/.config/swe-interview-coach/canvas.json and port 9999.)

Step 1 — Resolve the topic

Take $ARGUMENTS:

  • If ${CLAUDE_PLUGIN_ROOT}/library/sysdesign/<arg>.md exists: Read it and hold its full content as topic_source.
  • Else if $ARGUMENTS is non-empty: treat it as a free-form problem statement — hold it as topic_prompt.
  • If empty: Read the frontmatter id and difficulty of each file in ${CLAUDE_PLUGIN_ROOT}/library/sysdesign/*.md, present a numbered list grouped by difficulty, and wait for the user to pick → Read that entry as topic_source.

Step 2 — Parallel-session guard (canvas mode only)

Read the scene file, then: if the scene file's elements array is non-empty AND the file was modified within the last 30 minutes (find ~/.config/swe-interview-coach/canvas.json -mmin -30 prints the path), warn the user that another session may be mid-flight on this canvas, present a numbered choice, and wait for the answer:

The canvas has recent content — another session may be mid-flight. (1) proceed (resets the canvas) (2) cancel.

Step 3 — Set expectations + reset

Canvas mode — tell the user:

  • Describe your architecture out loud as you think; I'll sketch it live in your tab at http://localhost:9999.
  • You can also drag, rename, or add shapes yourself — I'll fold your edits in.
  • Ask for hints anytime — this is practice, not a test.

Then Write {"elements":[],"appState":{"viewBackgroundColor":"#ffffff"}} to the scene file to reset it.

Read the full file on GitHub · 110 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. 4d ago First seen · 110 lines · 63 tokens per session scan A f1a02f869b89

Subscribe to this mod's changes

practice-sysdesign is a command published in the GitHub repository kirilxd/swe-interview-coach (79 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,304 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 2026-08-30.