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 commands/kirilxd/swe-interview-coach/sysdesign-explaingit clone --depth 1 https://github.com/kirilxd/swe-interview-coachWrote 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/commands/kirilxd/swe-interview-coach/sysdesign-explain)<a href="https://agentmods.dev/commands/kirilxd/swe-interview-coach/sysdesign-explain"><img src="https://agentmods.dev/badge/commands/kirilxd/swe-interview-coach/sysdesign-explain.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 | $0.00073 | $0.01249 |
| Opus 5 | $0.00036 | $0.00624 |
| Sonnet 5 | $0.00015 | $0.00250 |
| Haiku 4.5 | $0.00007 | $0.00125 |
Grade A, and why
sysdesign-explain scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /sysdesign-explain.
Step 0 — Boot the canvas
Run bash "${CLAUDE_PLUGIN_ROOT}/scripts/ensure-canvas.sh" and parse its LAST line:
READY→ setcanvas_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, setcanvas_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 design
Take $ARGUMENTS as design.
- If empty: glob
${CLAUDE_PLUGIN_ROOT}/library/sysdesign/*.md, strip the path and.mdextension to get the available ids, list them, and ask the user to pick one. - If
${CLAUDE_PLUGIN_ROOT}/library/sysdesign/<design>.mdexists: Read it; hold its frontmatter and sections — they drive the whole walkthrough. - If it does not exist: present a numbered choice and wait for the answer:
Design "" not in library. (1) on-demand walkthrough (not canonical — relies on general knowledge; I'll say so) (2) cancel.
Step 2 — Set expectations
- Canvas mode: tell the user you'll explain in chat AND build the diagram live in their open tab at http://localhost:9999. If the tab looks blank, the Excalidraw library may still be loading from the CDN (first load needs internet) — coaching continues either way.
- Text mode: tell the user they get a structured markdown walkthrough instead.
Step 3 — Walkthrough (canvas mode)
Follow the library entry's section order: Requirements → Capacity estimation → High-level architecture → API design → Storage choices → Key components & deep dives → Common tradeoffs → Curveballs interviewers throw. (On-demand: follow the same eight sections from general knowledge, and restate up front that this is not a canonical entry.)
For each section:
a. Explain in chat — paraphrase the entry in your own voice; never dump it verbatim.
b. Read the scene file first and fold in any edits the user made in their tab (they sync silently within ~300 ms), then Write the merged cumulative scene — never Write from memory alone. Update the canvas by Writing the FULL cumulative scene to ~/.config/swe-interview-coach/canvas.json as {"elements":[…],"appState":{"viewBackgroundColor":"#ffffff"}}. The browser tab applies it within ~500 ms.
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 · 82 lines · 73 tokens per session scan A 5c9ae33bde01
sysdesign-explain is a command published in the GitHub repository kirilxd/swe-interview-coach (79 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,249 once invoked, about $0.0004 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.
Other commands, from other repositories
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
save
Save this conversation as a new or existing reusable context.
wp-polylang
Translate an existing WordPress site into a second language using Polylang.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.