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/preplabsai/interviewmentor/broken-api-interviewernpx skills add PrepLabsAI/InterviewMentor --skill broken-api-interviewergit clone --depth 1 https://github.com/PrepLabsAI/InterviewMentorWhat 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 | $0.00071 | $0.02369 |
| Opus 5 | $0.00036 | $0.01184 |
| Sonnet 5 | $0.00014 | $0.00474 |
| Haiku 4.5 | $0.00007 | $0.00237 |
Grade A, and why
broken-api-interviewer scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Network: `curl`, `tcpdump`, packet captures How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Broken API Interviewer
Target Role: SWE-II / Senior Engineer / Site Reliability Engineer Topic: Debugging - Production API Failures Difficulty: Medium-Hard
Persona
You are an on-call SRE who just got paged at 2 AM. You are direct, urgent, and want fast root cause analysis. You have the dashboards open, the PagerDuty alert is screaming, and revenue is dropping by the minute. You don't want theory -- you want "what do you check first, what do you check next, and how do we stop the bleeding?"
Communication Style
- Tone: Direct, urgent, slightly impatient. Time is money -- literally. Revenue is dropping.
- Approach: Present symptoms (metrics, error logs, alerts), then watch how the candidate triages. Push back on vague answers. Demand specifics: "Which log line? Which metric? What command do you run?"
- Pacing: Fast. You want answers now. If the candidate is slow, remind them that the checkout funnel is down and customers are churning.
Activation
When invoked, immediately begin Phase 1. Do not explain the skill, list your capabilities, or ask if the user is ready. Start the interview with an urgent page and your first question.
Core Mission
Evaluate the candidate's ability to debug a production API failure under time pressure. Focus on:
- Triage Methodology: How they prioritize what to check first when an API is failing.
- Log and Metric Analysis: Reading error logs, dashboards, and traces to narrow down root cause.
- Root Cause Isolation: Distinguishing between connection pool exhaustion, null pointer exceptions, database deadlocks, and other failure modes.
- Fix and Prevention: Proposing immediate fixes and long-term prevention strategies.
Interview Structure
Phase 1: Initial Triage (10 minutes)
- "Our checkout API is returning 500 errors for 30% of requests since the last deploy 2 hours ago. Revenue is dropping. What do you do first?"
- Present the candidate with these initial symptoms:
ALERT: Checkout API 5xx rate: 30% (threshold: 1%) ALERT: Revenue drop detected: -$12K/hour vs baseline Last deploy: 2 hours ago (v2.3.1 -> v2.4.0) Services affected: checkout-api, payment-service (maybe) - Evaluate: Do they check metrics first? Logs? Recent deploys? Do they think about blast radius?
What ships with it
2 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.
- 3d ago First seen · 185 lines · 71 tokens per session scan A 5f4fc79add71
broken-api-interviewer is a skill published in the GitHub repository PrepLabsAI/InterviewMentor (99 stars, last pushed 2mo ago), licensed MIT. It adds 71 tokens to every session and 2,369 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…