mock-interview-feature

A conversational practice interview feature with separate human-resources, professional, and manager styles. It supports spoken or typed answers, timed sessions, coaching based on the STAR answer method, and a post-session review.

In plain words
What is it for?
Practising interviews in English, choosing a session style and length, answering by voice or text, and reviewing answers after the session.
Why use it?
It lets candidates rehearse interview answers in a structured setting and receive explanations of their scores and suggestions for stronger answers.

Cursor rule for Claude Code

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 rules/eliornl/rolemule/mock-interview-feature
Clone the repo
git clone --depth 1 https://github.com/eliornl/rolemule

Made for: Claude Code.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,856 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 $0.00000 $0.01856
Opus 5 $0.00000 $0.00928
Sonnet 5 $0.00000 $0.00371
Haiku 4.5 $0.00000 $0.00186

Measured 2d ago against content hash a1bdbdf786f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mock-interview-feature 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 2d 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.

.claude/rules/mock-interview-feature.mdc · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Practice Interview (Mock Interview)

Standalone on-demand feature — not in the LangGraph workflow. Conversational practice for a workflow session using the user’s BYOK LLM. English only in v1.

Product summary

  • Tab: 9th application-detail tab Mock Session (data-tab="practice", #pane-practice) — after Interview (Optimize CV sits after Resume)
  • Styles: hr | pro | manager (required at start)
  • Duration: 10 | 15 | 20 minutes (default 15) — countdown from server ends_at, not fixed round count
  • Voice: browser Web Speech API (STT) + speechSynthesis (TTS); typed fallback always available
  • Submit UX: voice auto-submits after ~5s silence (VOICE_SILENCE_MS); typing uses Enter to send (Shift+Enter = newline); Submit answer button remains
  • Replay question / Mute this question as quiet session links; End early / Abort under More; confirm before End early
  • STAR coach always on; mid-session tips under the answer box (no mid-session topic coverage)
  • Debrief includes dimension score explanations in the UI, plus answer_reviews (stronger sample per candidate answer, capped at 6) with Copy; legacy weakest_answer_rewrite still filled for older clients
  • On timer expiry or End early, any draft answer (≥5 chars) is sent as final_answer on POST .../finish (not a separate /turn) so it is included in the debrief transcript
  • If End early is clicked while a turn is still in flight, the client queues finish, shows scoring UI, and finishes after the turn completes; finish also retries on 409 busy
  • Mic pauses while TTS speaks (avoids capturing interviewer audio)
  • While waiting for stream: current-question card shows Loading… until the first speak delta
  • Ending early / time-up: timer stops immediately and UI shows scoring state until debrief is ready
  • Debrief: overall score banner (full summary, no clamp), score breakdown (number on the right of each card), strengths/improvements, stronger sample answers — no Topics row, no Copy summary
  • Low-time coaching: last question (~2 min), short summary (~1 min), wrap-up (≤30s)
  • No audio upload / no server Whisper in v1

Read the full file on GitHub · 111 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. 2d ago First seen · 111 lines · 0 tokens per session scan A a1bdbdf786f9

Subscribe to this mod's changes

mock-interview-feature is a cursor rule published in the GitHub repository eliornl/rolemule (37 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,856 tokens. 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.