Borrowing it
Nothing to install: this file belongs to girik-chadha/interviewer-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/girik-chadha/interviewer-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/girik-chadha/interviewer-mcpWrote 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/instructions/girik-chadha/interviewer-mcp/claude-md)<a href="https://agentmods.dev/instructions/girik-chadha/interviewer-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/girik-chadha/interviewer-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/girik-chadha/interviewer-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/girik-chadha/interviewer-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00795 | $0.00795 |
| Opus 5 | $0.00398 | $0.00398 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
interviewer-mcp 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 9d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interviewer MCP — Claude Instructions
The Prep Menu (present at start + every phase transition)
- Company briefing · 2. Concept bootcamp (JD ∪ CV ∪ stack) · 3. Code deep-dive · 4. Mock interview · 5. Debrief — numbered options, user picks, progress marks shown.
Decision Tree — Which Tool When
"Prep me on " (new repo)
ingest_repo → get_progress (there may be history from a previous install) → start teach mode.
"Teach me my code" / "walk me through it"
list_sections → first uncovered section → get_code_section → MANDATORY deep format: (1) show the actual code in a code block, (2) block-by-block walkthrough of what AND why — lesson depth, never a summary; a one-liner is a failure, (3) end with one "an interviewer would ask" callout, (4) ask the user to explain the WHY back → only after a genuine attempt mark_covered → next section. One section per exchange, never dump several.
"Interview me" / "drill me" / "test me"
get_interview_targets (focus=weak_spots for returning users) → stay in character as a real interviewer → ground questions in code via get_code_section → after EVERY exchange log_interview_result → after 6–10 questions, exit character and debrief with get_progress.
"Let's continue" / "where were we" / "test me again"
get_progress FIRST. Open with specifics — coverage %, and the exact weak answers from last time. The user should feel remembered.
User pastes a job description
set_job_description → from then on: teach mode flags where code demonstrates JD skills, interview mode probes JD-required concepts the repo lacks.
"How am I doing?"
get_progress → summarize coverage, performance distribution, and weakest sections with their notes.
Context Management Rules
list_sectionsreturns metadata only (~50 tokens/section). Safe to call freely.get_code_sectionreturns real code — one section at a time, never loop over all sections.ingest_repocaps at 120 source files and 100KB/file;files_skippedin the response tells the user what was left out.- Tool errors include a
hintfield — follow it. The two common ones: repo not ingested (callingest_repo) and GitHub rate limit (setGITHUB_TOKEN).
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.
- 9d ago First seen · 51 lines · 795 tokens per session scan A 9a907c89efc8
interviewer-mcp CLAUDE.md is an instructions file published in the GitHub repository girik-chadha/interviewer-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 795 tokens to every session, about $0.0040 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.