ai-coding-interview

A practice guide for AI-assisted backend coding interviews, with guided rehearsals, timed mock interviews, and reviews of existing work.

In plain words
What is it for?
Use it to rehearse or review an AI coding interview, including realistic interviewer, coach, and coding-agent roles.
Why use it?
It provides structured practice and evidence-based feedback while keeping the candidate responsible for the requirements, prompts, code, testing, and explanation.

Skill for Claude CodeCodex

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 skills/saski/arnesto/ai-coding-interview
Any agent
npx skills add saski/arnesto --skill ai-coding-interview
Clone the repo
git clone --depth 1 https://github.com/saski/arnesto

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,584 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 $0.00050 $0.01584
Opus 5 $0.00025 $0.00792
Sonnet 5 $0.00010 $0.00317
Haiku 4.5 $0.00005 $0.00158

Measured 2d ago against content hash d1a35d196b0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-coding-interview 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.

.agents/skills/ai-coding-interview/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Coding Interview

Guide the candidate toward a small working solution while preserving candidate ownership of the contract, prompts, code, validation, and explanation. Do not replace candidate judgment with unsolicited implementation.

When the target is the current Datadog AI Coding loop, read references/datadog-ai-coding-rubric.md before presenting an exercise or scoring a session.

Select the session mode

State the mode before presenting an exercise:

  • Guided rehearsal teaches the workflow, asks one question at a time, and gives concise feedback. It is not an independent baseline.
  • Timed mock uses the interview clock without coaching. Answer contract questions as the interviewer, execute only candidate-directed AI requests, give phase checkpoints, and evaluate after the close.
  • Review inspects an existing prompt, transcript, solution, and evidence without starting implementation.

Default to guided rehearsal when the user asks for guidance or is learning the workflow. Never start a timer until the user explicitly says to start.

Preserve role boundaries

Label role changes when ambiguity is possible:

  • Interviewer answers clarification questions without volunteering a solution.
  • Coach teaches and recovers the process only in guided rehearsal.
  • Coding agent plans or edits only within the candidate's explicit prompt.

If interviewer answers were spoken outside the AI conversation, require the candidate to transfer them as concise clarified requirements. Do not assume the coding agent heard the verbal discussion.

Establish the contract

Read the complete supplied prompt and preserve it as the source of truth. Ask only questions whose answers can change code, tests, or complexity:

  • public inputs, outputs, and examples;
  • required fields, types, ranges, and error contracts;
  • partial versus atomic processing;
  • retry, idempotency, and ordering semantics;
  • in-memory versus persistent state;
  • synchronous, concurrent, or asynchronous execution;
  • scale boundaries that affect implementation;
  • ranking, limits, pagination, and deterministic tie-breaking;
  • required behavior, extensions, and success criteria.

Read the full file on GitHub · 171 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 171 lines · 50 tokens per session scan A d1a35d196b0f

Subscribe to this mod's changes

ai-coding-interview is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed 6d ago), licensed Unlicense. It adds 50 tokens to every session and 1,584 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

pixir-delegate

Use Pixir as a headless subagent runtime from Claude Code or any harness with skill ! preprocessing (Codex roots and other no-hydration hosts use pixir-delegate-codex instead) — one-shot workers (pixir --json), parallel fan-out to N children (pixir delegate --spec), resumable steering (pixir resume), evidence…

Ranvier-Technologies/pixir · 126 tokens

pixir-delegate-codex

Use when a Codex CLI/Desktop root should fan out subagents, delegate to Pixir workers, run parallel workers, or manage a resident delegation daemon via Pixir Delegate; covers Codex preflight, AGENTS.md, approvals/sandbox, dry-run, daemon start/status/attach/cancel, closure evidence, and audited single-run execution…

Ranvier-Technologies/pixir · 89 tokens

pixir-diagnostics

Diagnose Pixir and T3 Code Pixir incidents from local canonical evidence. Use when a Pixir run, ACP/T3 thread, subagent/workflow, provider replay, or daily-driver dogfood session appears stuck, inconsistent, missing tool output, or hard to classify.

Ranvier-Technologies/pixir · 61 tokens

readonly-review

Run a no-network read-only review practice with two explorer steps and one synthesis step.

Ranvier-Technologies/pixir · 20 tokens

pixir-delegate-native

Delegate work to subagents from INSIDE a Pixir session using the native Subagent tools (spawnagent, waitagent, closeagent, listagents, sendinput) instead of shelling out to the pixir CLI. Use when you are a Pixir session that needs to fan out parallel workers, steer a child, or run skill-backed workflow templates …

Ranvier-Technologies/pixir · 89 tokens

repo-contracts-and-boundaries

Use when turning architecture, layering, ownership, dependency direction, schemas, structural metrics, quality thresholds, baselines, allowlists, or generated quality snapshots into repository checks.

yfge/agent-harness-skills · 41 tokens