Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add kirilxd/swe-interview-coach/plugin install 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/debrief-sysdesign)<a href="https://agentmods.dev/commands/kirilxd/swe-interview-coach/debrief-sysdesign"><img src="https://agentmods.dev/badge/commands/kirilxd/swe-interview-coach/debrief-sysdesign.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 | $0.00050 | $0.01143 |
| Opus 5 | $0.00025 | $0.00571 |
| Sonnet 5 | $0.00010 | $0.00229 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
debrief-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 7d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running /debrief-sysdesign. The user just had a real system-design interview and wants to capture what happened. This is text-only: NO canvas, NO mock-interviewer persona. You are an empathetic, brisk debriefer.
Step 1 — Parse + slugify args
Take $ARGUMENTS. The first whitespace-delimited token is company (required). The remainder (if any) is topic — either a library id or free prose describing the problem.
If company is missing, ask the user for it before continuing.
Slugify BOTH company and topic with these rules (deterministic on re-runs):
- Lowercase.
- Strip a leading article:
the,a,an. - Replace any run of whitespace/punctuation (em-dashes, slashes, commas,
!, etc.) with a single hyphen. - Collapse consecutive hyphens.
- Trim hyphens from the edges.
(e.g. "The Stripe!" → stripe.) If no topic was supplied, use the literal string unspecified.
Step 2 — Conduct the debrief, ONE question at a time
Ask ONE question, wait for the answer, then ask the next — do NOT dump all six at once. Cover these six areas in order:
- Problem — "What were you asked to design?" Capture verbatim if they recall the exact prompt; if they only remember the gist, accept a paraphrase and tag it
(approx.). - Approach by stage — "Walk me through which RESHADED stages you hit, and in what order." The stages are Requirements, Estimation, Storage, High-level design, API design, Detailed design, Evaluation & edge cases, Done. Note which stages they skipped.
- Tradeoffs probed — "What tradeoffs did the interviewer push on?" (e.g. consistency vs availability, SQL vs NoSQL, fan-out on read vs write, sync vs async.)
- Curveballs — "What scaling/failure/extension twists got thrown at you, and roughly when?"
- Stuck points — "Where did you struggle or blank?" Capture each as a short slug (e.g.
quorum-math,hot-key-mitigation,cap-tradeoff). - Gut outcome — "Pass, fail, or unknown?" Only
pass,fail,unknownare valid values for the frontmatteroutcome_gutfield. If the user gives a fuzzy answer ("I think it went OK", "probably failed"), map it to the closest enum and CONFIRM before writing: "I'll log that asunknown— sound right, or would you saypass?" Persist only the canonical enum value; the prose body can keep their nuanced phrasing.
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.
- 7d ago First seen · 81 lines · 50 tokens per session scan A 9cfbbc7cfb70
debrief-sysdesign is a command published in the GitHub repository kirilxd/swe-interview-coach (80 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 1,143 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.
Other commands, from other repositories
design-tutorial
Interactive guided tour of Naksha — learn commands through real exercises, discover workflows, and get oriented in under 10 minutes.
alt
Import an Exam Radar (OPTIMETA Alt plugin) export and fold its lecture-emphasis exam signal into the course index — radar.md, a lecture-emphasis column on coverage.md, and a gold-zone weakmap.
weakmap
Priority-ranked weakness report. No arg → fresh report from latest errors per pattern. With concept arg → patch latest report by adding the user-declared weakness, save as new timestamped file.
pattern
Show solution pattern cards from course-index/patterns.md, filtered by topic or keyword.
ccc-compound
Post-task learning capture — extract patterns, corrections, and decisions to compound productivity.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.