practice

practice is a command for coding agents from noamseg/interview-coach-skill. It costs 0 tokens per session (3,161 once invoked), scanned A, original, MIT.

An interview-practice command with drills that become harder as the candidate progresses. The exercises cover concise answers, skeptical follow-up questions, topic changes, missing examples, role-specific questions, panels, pressure, and technical explanations.

In plain words
What is it for?
Use it to rehearse interview stories at different lengths, handle pushback, explain technical decisions, and practice under realistic pressure.
Why use it?
It turns interview preparation into repeated practice for specific difficult situations rather than relying only on reading questions or memorizing answers.

Command

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/noamseg/interview-coach-skill/practice
Clone the repo
git clone --depth 1 https://github.com/noamseg/interview-coach-skill

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 practice

README.md
[![agentmods](https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/practice.svg)](https://agentmods.dev/commands/noamseg/interview-coach-skill/practice)
Your own site
<a href="https://agentmods.dev/commands/noamseg/interview-coach-skill/practice"><img src="https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/practice.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 3,161 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 $0.03161
Opus 5 $0.00000 $0.01580
Sonnet 5 $0.00000 $0.00632
Haiku 4.5 $0.00000 $0.00316

Measured 4d ago against content hash 2d4ab4e36cbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

practice 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.

references/commands/practice.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

practice — Practice System

Show menu with progression status:

Practice Menu (stages 1-8 are gated by progression)
1) practice ladder     — Constraint drills: tell the same story at 30s, 60s, 90s, 3min
2) practice pushback   — Handle skepticism, interruption, "so what?" pressure
3) practice pivot      — Redirect when a question doesn't match your prep
4) practice gap        — Handle "I don't have an example for that" moments
5) practice role       — Role-specific specialist scrutiny
6) practice panel      — Multiple interviewer personas simultaneously
7) practice stress     — Role-specific high-pressure simulation
8) practice technical  — Thinking out loud, clarification-seeking, tradeoff articulation (optional — system design/mixed format only)

Standalone (not gated by progression):
•  practice retrieval  — Rapid-fire question-to-story matching under time pressure (requires 8+ stories)

Use references/role-drills.md for role-specific pressure prompts and technical communication drills.

Drill Progression Ladder

Drills are ordered by prerequisite difficulty. Do not advance until the candidate meets the gating threshold:

Stage Drill Gate to advance Prerequisite
1 Ladder Structure ≥ 3 on 3 consecutive rounds None
2 Pushback Credibility ≥ 3 under pressure Stage 1
3 Pivot Relevance ≥ 3 when redirected Stage 2
4 Gap Credibility ≥ 3 with honest gap handling Stage 2
5 Role Substance ≥ 3 under specialist scrutiny Stages 1-3
6 Panel All dimensions ≥ 3 with multiple personas Stages 1-4
7 Stress All dimensions ≥ 3 under maximum pressure Stages 1-5
8 (optional) Technical Structure + Substance ≥ 3 in technical communication Stages 1-3. Only for candidates with system design, case study, or technical+behavioral mix interviews.

If a candidate requests a drill above their current stage, flag it: "You can absolutely try this, but your [dimension] scores suggest you'd get more value from [prerequisite drill] first. Want to start there, or jump ahead anyway?" Respect their choice but name the risk.

Read the full file on GitHub · 179 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 · 179 lines · 0 tokens per session scan A 2d4ab4e36cbe

Subscribe to this mod's changes

practice is a command published in the GitHub repository noamseg/interview-coach-skill (2,092 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,161 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.