grind

grind is a command for coding agents from aayushostwal/nexus. It costs 0 tokens per session (948 once invoked), scanned B, original, MIT.

An interactive practice session for technical or behavioural job interviews, based on a chosen subject, role, and interview format.

In plain words
What is it for?
It helps candidates prepare for topics such as algorithms, system design, machine learning, and behavioural interviews, tailored to a specific job level and company.
Why use it?
It helps reveal weak spots and common mistakes through challenging questions instead of passive reading.

Command

Part of the nexus plugin — 10 skills, 2 commands, 14 agents shipped together

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 commands/aayushostwal/nexus/grind
Clone the repo
git clone --depth 1 https://github.com/aayushostwal/nexus

Or install nexus, the plugin that ships this one along with the rest of its 10 skills, 2 commands, 14 agents.

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.

agentmods badge for grind

README.md
[![agentmods](https://agentmods.dev/badge/commands/aayushostwal/nexus/grind.svg)](https://agentmods.dev/commands/aayushostwal/nexus/grind)
Your own site
<a href="https://agentmods.dev/commands/aayushostwal/nexus/grind"><img src="https://agentmods.dev/badge/commands/aayushostwal/nexus/grind.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 948 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00948
Opus 5 $0.00000 $0.00474
Sonnet 5 $0.00000 $0.00190
Haiku 4.5 $0.00000 $0.00095

Measured 4d ago against content hash ec9ad3eacf24, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

grind scanned grade B 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 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- React honestly and briefly to each answer (correct / partially correct / off-base) before the next move — but don't lecture mid-session; save full teaching for the final Feedback.
commands/grind.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/grind — Interview Grinding Command

Purpose: Turn any concept or document into a live, adversarial interview drilling session, tailored to a specific role and interview format.


Inputs

  • Subject (required): A concept (e.g. "Consistent Hashing", "Backpropagation") or a Document (paste text / upload).
  • Role (optional): e.g. "Google L5 Software Engineer", "Meta E5 ML Engineer". If not given, ask.
  • Interview Type (optional): e.g. "Googliness", "ML System Design", "DSA", "Behavioral", "System Design", "Bar Raiser". If not given, ask.

If Role or Interview Type is missing, ask one short clarifying question covering both before proceeding. Do not proceed with generic assumptions.


Step 1 — Recon (before asking any interview question)

  1. Search the web for the Subject — get current definitions, common variants, edge cases, recent developments, and the 3-5 things candidates most often get wrong.
  2. Search the web for the Role — get the current interview format, evaluation rubric/leveling expectations, and what that specific bar (e.g. "L5", "E5", "Staff") is known to probe for at that company.
  3. Silently synthesize: which parts of the Subject are most likely to be tested at this Role's level, and in what interview format.

Do not show raw search results to the user — just use them to calibrate difficulty and question selection.


Step 2 — Run the Grind

Act as a real interviewer, not a tutor. Tone: rigorous, terse, slightly skeptical — the way a real bar-raiser sounds. No hand-holding, no giving away the answer.

Alternate between two move types, chosen based on how the candidate answered:

  • Cross-question in depth — when the candidate's last answer was incomplete, hand-wavy, or has an exploitable gap. Push on: edge cases, failure modes, trade-offs, "why not X instead", scale/constraints, "what if requirement Y changes".
  • New question, adjacent subject — when the candidate nailed the current thread. Move to a related-but-distinct area within the same Subject/Role scope to test breadth.

Read the full file on GitHub · 77 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. 4d ago First seen · 77 lines · 0 tokens per session scan B ec9ad3eacf24

Subscribe to this mod's changes

grind is a command published in the GitHub repository aayushostwal/nexus (18 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 948 tokens. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.