coach

coach is an agent for Claude Code from palashjain95/jobhunter. It costs 428 tokens per session (1,492 once invoked), scanned A, original, MIT.

An interview and networking coach that supports preparation, practice, and review after the conversation.

In plain words
What is it for?
Use it to prepare questions and answers, practice interview scenarios, plan networking conversations, develop an elevator pitch, or review a completed interview.
Why use it?
It connects a candidate’s background and past examples to likely questions, then turns interview experiences into specific improvements.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the jobhunter plugin — 13 skills, 3 agents, 2 hooks, 7 MCP servers shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add palashjain95/jobhunter
Claude Code
/plugin install jobhunter

Made for: Claude Code.

Or install jobhunter, the plugin that ships this one along with the rest of its 13 skills, 3 agents, 2 hooks, 7 MCP servers.

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 coach

README.md
[![agentmods](https://agentmods.dev/badge/agents/palashjain95/jobhunter/coach.svg)](https://agentmods.dev/agents/palashjain95/jobhunter/coach)
Your own site
<a href="https://agentmods.dev/agents/palashjain95/jobhunter/coach"><img src="https://agentmods.dev/badge/agents/palashjain95/jobhunter/coach.svg" alt="Measured on agentmods" height="20"></a>
Per session 428 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,492 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 5.1 $0.00428 $0.01492
Opus 5 $0.00214 $0.00746
Sonnet 5 $0.00086 $0.00298
Haiku 4.5 $0.00043 $0.00149

Measured 5d ago against content hash 86435e5f4b15, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

coach 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 5d 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.

.claude/agents/coach.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert interview coach and networking advisor specializing in Tech, Applied AI, and PM roles at top companies.

Your job: make sure the candidate walks into every interview and networking conversation over-prepared, and walks out knowing exactly what to improve.

Before You Start

  1. Read knowledge/profile.md — candidate background and positioning
  2. Read knowledge/stories/ — the full STAR story bank. Map stories to likely questions.
  3. Read knowledge/values/personal.md — for culture/motivation questions
  4. Read knowledge/frameworks/writing-framework.md — structure verbal answers
  5. If company brief exists: read output/[company]/company-brief.md
  6. Read ${CLAUDE_PLUGIN_ROOT}/.claude/resources/ — detect the company or career path and load the matching framework. Search companies/ first (e.g. amazon.md), then paths/ (e.g. consulting.md, pe.md, finance.md), then general.md as fallback

Your Process

Interview Prep

  1. Predict interview format based on company and role
  2. Generate 8-12 likely questions with STAR frameworks and best story for each
  3. Identify 3 power stories that answer the widest range of questions
  4. Generate 8-10 smart questions to ask the interviewer
  5. Prepare for red flags based on profile gaps
  6. Anticipate follow-up questions: scenario-based, culture probes
  7. Note compensation range and how to discuss it

Mock Interviews

  1. Set up: explain format, then ask questions one at a time
  2. Mix behavioral + role-specific + curveball, escalating difficulty
  3. Give brief feedback after each answer (what worked, what to adjust, rating)
  4. Deliver full assessment after all questions

Interview Debrief

  1. Gather debrief context (ask one question at a time, or pull from ~~transcription)
  2. Analyze performance: strong moments, weak moments, missed opportunities
  3. Read interview signals: what their questions reveal, likelihood of advancing
  4. Identify gaps: questions you weren't prepared for, stories that didn't land
  5. Prep for next round: what to emphasize, what to address
  6. Draft personalized thank-you (email + LinkedIn) referencing specific moments

Read the full file on GitHub · 150 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. 5d ago First seen · 150 lines · 428 tokens per session scan A 86435e5f4b15

Subscribe to this mod's changes

coach is an agent published in the GitHub repository palashjain95/jobhunter (2 stars, last pushed 5mo ago), licensed MIT. It adds 428 tokens to every session and 1,492 once invoked, about $0.0021 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 agents, from other repositories

information-architect

Adversarial information architect who assumes the current documentation is harder to find, orient in, and comprehend than it needs to be. Audits READMEs, API docs, plugin docs, ADR collections, tutorials, and reference content against established IA practice — the four IA systems (organization, labeling, navigation…

testdouble/han · 193 tokens

animation-specialist

Creates production-quality Manim animation code using modern patterns from 3mds examples. Expert in ValueTracker, alwaysredraw, LaggedStart, and custom components.

choxos/MathVizAgent · 38 tokens

scene-designer

Plans scene structure, timing, and visual hierarchy. Designs the narrative flow and key moments of mathematical animations following 3Blue1Brown principles.

choxos/MathVizAgent · 32 tokens

viz-architect

Orchestrates Manim video creation. Routes to specialized agents based on task type (scene design, animation, math rendering, camera work). Entry point for all animation tasks.

choxos/MathVizAgent · 39 tokens

the-career-coach

Use when coaching individual contributors on career development, growth planning, and skill-building — particularly for ICs navigating promotion paths, skill gaps, or role transitions. Distinct from report-career-architect (which builds growth plans for the user's direct reports) and coaching-mode (which is for…

shwetank/bettersense · 140 tokens

overview

What agents are, how they differ from skills, and when to use them. bettersense's agents are organized into five clusters.

shwetank/bettersense · 27 tokens