interview-prep-feature

An optional, static interview-preparation guide generated by a separate agent. It runs in the background using information such as job analysis and company research, and it is separate from a timed practice interview.

In plain words
What is it for?
Use it to build the Interview tab’s preparation material, prevent duplicate background jobs with a Redis lock, and cache or refresh the generated guide.
Why use it?
It lets preparation content be generated on demand without adding another step to the main workflow or creating duplicate concurrent generations.

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/interview-prep-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 1,137 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 $0.01137
Opus 5 $0.00000 $0.00568
Sonnet 5 $0.00000 $0.00227
Haiku 4.5 $0.00000 $0.00114

Measured yesterday against content hash a2c45cdf6863, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interview-prep-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 yesterday.

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/interview-prep-feature.mdc · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interview Prep Feature

Static on-demand guide on the Interview tab (process / questions / preparation). Not the timed conversational Mock Session tab — see mock-interview-feature.mdc.

Standalone Agent (NOT in LangGraph workflow)

InterviewPrepAgent in agents/interview_prep.py is invoked on-demand, independently of the main 5-agent LangGraph workflow. It is called from api/interview_prep.py via BackgroundTasks.

agent = InterviewPrepAgent()
result = await agent.generate(
    job_analysis=workflow_session.job_analysis or {},
    company_research=workflow_session.company_research or {},
    profile_matching=workflow_session.profile_matching or {},
    user_profile=workflow_session.user_data or {},
    user_api_key=user_api_key,  # BYOK
)

Background Generation with Atomic Redis Locking

Use the Redis lock to prevent duplicate concurrent generations:

from utils.cache import (
    is_interview_prep_generating,
    set_interview_prep_generating,   # Returns False if already locked
    clear_interview_prep_generating,
    cache_interview_prep,
    invalidate_interview_prep,
)

# Atomically claim the slot (NX SET)
claimed = await set_interview_prep_generating(session_id)
if not claimed:
    raise APIError(ErrorCode.RES_3001, "Interview prep generation already in progress", status_code=409)

# Always pass user_id so WebSocket broadcasts work inside the background task
background_tasks.add_task(_generate_background, session_id=session_id, user_id=str(user_id), ...)

Always clear the lock in finally and broadcast lifecycle events:

from api.websocket import (
    broadcast_interview_prep_started,
    broadcast_interview_prep_complete,
    broadcast_interview_prep_error,
)

async def _generate_background(
    session_id: str,
    user_id: Optional[str] = None,
    user_api_key: Optional[str] = None,
):
    try:
        async with get_session() as db:
            workflow_session = await _load_session(db, session_id)
            ws_user_id = user_id or str(workflow_session.user_id)

            await broadcast_interview_prep_started(ws_user_id, session_id)

            # generate and save
            workflow_session.interview_prep = result
            flag_modified(workflow_session, "interview_prep")
            await db.commit()
            await cache_interview_prep(session_id, result)

            await broadcast_interview_prep_complete(ws_user_id, session_id)
    except Exception as e:
        logger.error(f"Interview prep failed: {e}", exc_info=True)
        await broadcast_interview_prep_error(ws_user_id, session_id, "Interview prep generation failed")
    finally:
        await clear_interview_prep_generating(session_id)

Read the full file on GitHub · 126 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. yesterday First seen · 126 lines · 0 tokens per session scan A a2c45cdf6863

Subscribe to this mod's changes

interview-prep-feature is a cursor rule published in the GitHub repository eliornl/rolemule (37 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,137 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.

Related

Other cursor rules, from other repositories

cursorrules

Agent2 is a framework for building production AI agents with typed HTTP APIs. PydanticAI handles the agent loop. Agent2 handles everything else: API, auth, pause/resume, approvals, provider routing, knowledge search.

Artesiana/agent2 · 399 tokens

product-manager

Holistic product leader who owns the full product lifecycle — from discovery and strategy through roadmap, stakeholder alignment, go-to-market, and outcome measurement. Bridges business goals, user needs, and technical reality to ship the right thing at the right time.

Treevu-ai/cli-market-world · 5,350 tokens

api-tester

Expert API testing specialist focused on comprehensive API validation, performance testing, and quality assurance across all systems and third-party integrations.

Treevu-ai/cli-market-world · 23 tokens

developer-advocate

Expert developer advocate specializing in building developer communities, creating compelling technical content, optimizing developer experience (DX), and driving platform adoption through authentic engineering engagement. Bridges product and engineering teams with external developers.

Treevu-ai/cli-market-world · 38 tokens

architectural-and-structural-rules

The project follows a layered architecture with clear separation of concerns.

mrharishkumar/fastapi-cursor-boilerplate · 559 tokens

angular-20

This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.

angular/angular · 0 tokens