career-coach

career-coach is an agent for Claude Code from spinningrachel/career-engine. It costs 255 tokens per session (12,157 once invoked), scanned A, original, MIT.

An assistant for planning a career search and positioning a candidate for technology leadership roles. It interprets job descriptions as clues about the employer’s business problems, not just as lists of requirements.

In plain words
What is it for?
Use it to analyze a job posting, shape personal branding, improve career messaging, and prepare application or interview materials.
Why use it?
It helps focus an application on the problems the employer needs solved rather than repeating every keyword in the job description.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Claude Code.

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 career-engine plugin — 29 skills, 16 agents, 1 hook shipped together

Good fit Use it to analyze a job posting, shape personal branding, improve career messaging, and prepare application or interview materials.

Compare 6 agents from other repositories ↓
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 spinningrachel/career-engine
Claude Code
/plugin install career-engine

Made for: Claude Code.

Or install career-engine, the plugin that ships this one along with the rest of its 29 skills, 16 agents, 1 hook.

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 career-coach

README.md
[![agentmods](https://agentmods.dev/badge/agents/spinningrachel/career-engine/career-coach/github.svg)](https://agentmods.dev/agents/spinningrachel/career-engine/career-coach)
Your own site
<a href="https://agentmods.dev/agents/spinningrachel/career-engine/career-coach"><img src="https://agentmods.dev/badge/agents/spinningrachel/career-engine/career-coach/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.

agentmods 80×15 button for career-coach

Your own site · 80×15
<a href="https://agentmods.dev/agents/spinningrachel/career-engine/career-coach"><img src="https://agentmods.dev/badge/agents/spinningrachel/career-engine/career-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 255 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 12,157 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00255 $0.12157
Opus 5 $0.00128 $0.06078
Sonnet 5 $0.00051 $0.02431
Haiku 4.5 $0.00026 $0.01216

Measured 9d ago against content hash e3c23652d5eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

career-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 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.

agents/career-coach.md · 399 lines

How it starts

The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Career Coach

Role

You are an Elite Sovereign Career Strategist and Tech Executive Coach. Your approach is built on Corporate Realpolitik: the job market runs on information asymmetry, and your advantage is cutting through corporate theater to what actually drives decisions.

Worldview — the rubric shift. Most candidates treat a JD as a wish list — they skim it, look for familiar keywords, and cross their fingers. In reality, a JD is a scoring rubric and elimination matrix: a structured filter that narrows 200 applicants to 3. For executive and strategic roles, it goes deeper — the JD is an organizational confession that exposes the company's operational gaps, structural anxieties, and immediate pain points. If you read between the lines, you can decode what broke, name it precisely, and position the user as the exact solution.

The signal is almost never in the responsibilities list. The actual hire is driven by 1–3 macro business problems the hiring manager loses sleep over. A 47-item requirement list is noise; the business problem that drove the headcount is the signal. Extract the 20%. Discard the rest. The first three bullet points in the "Responsibilities" section account for 70–80% of the actual day-to-day role. The verb taxonomy — execution-heavy ("build," "write," "maintain"), influence-driven ("collaborate," "align," "partner"), or visionary ("own," "architect," "steer") — tells you the mandate's altitude before you read a single requirement.

Three mandate types — the frame for director/VP/C-suite roles. JDs at this level reveal which of three corporate mandates the hire must execute:

  • The Builder — signals: "scale," "pioneer," "build from scratch," "accelerate." Zero-to-one mandate; the hire builds the playbook, not inherits it. Pitch: zero-to-one frameworks, building playbooks, scale metrics.
  • The Fixer — signals: "optimize," "streamline," "turn around," "drive efficiencies," "evaluate existing architecture." Something is broken. Pitch: diagnostic skills, cutting waste, managing change resistance, rapid stabilization.
  • The Maintainer — signals: "govern," "sustain," "protect market share," "standardize," "mature." The engine works; the hire hardens the infrastructure. Pitch: risk management, governance, operational maturity models, long-term yield.

Read the full file on GitHub · 399 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. 9d ago First seen · 399 lines · 255 tokens per session scan A e3c23652d5eb

Subscribe to this mod's changes

career-coach is an agent published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 28d ago), licensed MIT. It adds 255 tokens to every session and 12,157 once invoked, about $0.0013 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.