What is interview-prep-template CLAUDE.md?

A set of instructions for maintaining an interview-preparation wiki that turns raw notes and recordings into reusable answers and concepts. A wiki is an organized collection of linked pages.

Adding interview notes, processing them into markdown pages, querying the resulting knowledge base, and checking for missing or outdated information.

It separates untouched source material from the synthesized wiki, making preparation knowledge easier to maintain and reuse.

interview-prep-template CLAUDE.md — Instructions file for coding agents by AbhiK189: A set of instructions for maintaining an interview-prep

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 instructions/abhik189/interview-prep-template/claude-md

Clone the repo

git clone --depth 1 https://github.com/AbhiK189/interview-prep-template

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/abhik189/interview-prep-template/claude-md.svg)](https://agentmods.dev/instructions/abhik189/interview-prep-template/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/abhik189/interview-prep-template/claude-md"><img src="https://agentmods.dev/badge/instructions/abhik189/interview-prep-template/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 4,480 This file is loaded in full into every session.

When invoked 4,480 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5	$0.04480	$0.04480
Opus 5	$0.02240	$0.02240
Sonnet 5	$0.00896	$0.00896
Haiku 4.5	$0.00448	$0.00448

Measured 4d ago against content hash 0416aa2b747a, 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-template CLAUDE.md 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 4d 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.

Origin

This is a copy

100% identical to interview-prep-template AGENTS.md — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Interview Prep Wiki

Purpose

A personal interview prep wiki on a three-layer system (Karpathy's pattern):

Layer 1 — sources/: raw material you drop in (mock-interview recordings & transcripts, real-interview & career-chat notes, reading, project descriptions). Content is immutable — you own it, I never edit it. An unprocessed file lives directly in its source folder (e.g. sources/projects/); once I've mined it, I move it into that folder's processed/ subfolder.
Layer 2 — wiki/: LLM-maintained markdown synthesizing the sources into reusable answers, frameworks, and concepts. I (the LLM) own this entirely.
Layer 3 — this file: how I operate the wiki.

The loop: you drop materials into sources/; I lift the durable content into wiki/ and move the source into processed/; you query me and I answer from the wiki. On lint I flag gaps and stale claims. The wiki is the persistent, compounding artifact.

Targets: interviews for [replace with your target functions — e.g. product management, GTM strategy & operations, engineering] across [N] companies.

Directory layout

sources/                      ← Layer 1 (raw material — content is immutable)
  recordings/                   audio/video of mock interviews       (drop unprocessed files here)
    processed/                    move here once mined
  transcripts/                  verbatim text from mock recordings   (drop unprocessed files here)
    processed/                    move here once mined
  interview-notes/              notes/recall of an interview or chat (drop unprocessed files here)
    processed/                    move here once mined
  reading/                      articles, book chapters, AI news     (drop unprocessed files here)
    processed/                    move here once mined
  projects/                     user's detailed project descriptions (drop unprocessed files here)
    processed/                    move here once mined

wiki/                         ← Layer 2 (you own)
  companies/<company>/
    overview.md                 strategy, products, recent moves
    <role>.md                   role-specific JD, role evaluation framework
  behavioral/<question>.md      one file per potential behavioral question
  frameworks/<name>.md          reusable analytical templates (GTM, AI transformation, prioritization, etc.)
  ai-knowledge/<name>.md        AI domain knowledge
  interview-debriefs/<role>/
  <round>-<date>-<role>.md      per-interview debriefs

CLAUDE.md                     ← this file
index.md                      ← catalog of every wiki page
log.md                        ← chronological record of ingests, lints, structural changes

Read the full file on GitHub · 307 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.

4d ago First seen · 307 lines · 4,480 tokens per session scan A 0416aa2b747a

Subscribe to this mod's changes

interview-prep-template CLAUDE.md is an instructions file published in the GitHub repository AbhiK189/interview-prep-template (21 stars, last pushed 2mo ago), licensed MIT. It adds 4,480 tokens to every session, about $0.0224 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to interview-prep-template AGENTS.md, differing in 4 lines, and is treated as a copy.

Learning and teaching Writing and docs

interview-prep-template CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

How it starts

CLAUDE.md — Interview Prep Wiki

Purpose

Directory layout

What this file has done since we first saw it

Other instructions, from other repositories

open-dictionary AGENTS.md

ab900 CLAUDE.md

canvas-lms-mcp AGENTS.md

obsidian-university-workflow CLAUDE.md

anki-mcp-server CLAUDE.md

claude-certified-architect-guide CLAUDE.md