career-setup

career-setup is a skill for Claude Code from davekilleen/Dex. It costs 18 tokens per session (4,712 once invoked), scanned A, original, MIT.

A career-development setup for recording your job description, career ladder, performance reviews, and goals.

In plain words
What is it for?
Use it to define your role, track development goals, prepare for reviews, and compare your work with the next career level.
Why use it?
It gives career planning a consistent place and structure instead of leaving expectations and progress scattered across notes.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; installed under .agents/ (shared by several agents).

Good fit Use it to define your role, track development goals, prepare for reviews, and compare your work with the next career level.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/davekilleen/dex/career-setup
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.

Any agent
npx skills add davekilleen/Dex --skill career-setup
Clone the repo
git clone --depth 1 https://github.com/davekilleen/Dex

Made for: Claude Code.

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-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/davekilleen/dex/career-setup/github.svg)](https://agentmods.dev/skills/davekilleen/dex/career-setup)
Your own site
<a href="https://agentmods.dev/skills/davekilleen/dex/career-setup"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/career-setup/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-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/davekilleen/dex/career-setup"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/career-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,712 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 $0.00018 $0.04712
Opus 5.5 $0.00007 $0.01885
Sonnet 5.5 $0.00004 $0.00942
Haiku 4.5 $0.00002 $0.00471

Measured 1mo ago against content hash bb7ccf5fc304, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

career-setup 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 1mo 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/_available/capabilities/career/skills/career-setup/SKILL.md · 752 lines

How it starts

The opening of the file, as written. The whole thing — 752 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Initialize the enabled Career room in Dex. Captures your job description, career ladder, latest review, and long-term growth goals to create a foundation for ongoing career coaching.

Usage

/career-setup

One-time setup (or re-run to update). Creates your Career folder and baseline context.


Method

Verify the Career room and available integrations, then ask which setup inputs the user wants to provide. Minimize sensitive collection and retain the source path, source date, retrieval as-of time, and uncertainty for each job description, ladder, review, and goal. Normalize all evidence to the portable 05-Areas/Career/Evidence/ path. Stage each destination independently, show the exact complete bytes, obtain explicit confirmation immediately before writing, and read the file back before proceeding. Treat the evidence hook as a read-only candidate detector; it never supplies consent or writes on the user's behalf.

Output contract

Return room and MCP readiness, the inputs received and deliberately omitted, provenance and unknowns, the exact proposed file set, and a per-file mutation state. Each destination must be labelled not requested, awaiting confirmation, verified from read-back, or failed; never summarize a partially written setup as complete. Include hook availability separately from evidence-save status. The completion summary must list only verified paths, preserve every pre-existing conflict, and explain the next safe recovery step for any failed or declined file.

Step 0: Verify the room and integrations

Before collecting or writing career information, read the authoritative capability state in System/user-profile.yaml and verify that the Career room is enabled. If it is disabled, stop and explain how to enable it; do not create a partial room. Record the check date and as-of time. Separately verify whether the Career MCP tools are available. If the room is enabled but MCP is unavailable or its state is unknown, say so and use only the local files that can be read; do not present a local-only result as an MCP result.

Read the full file on GitHub · 752 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. 1mo ago Changed · +2 lines bb7ccf5fc304
  2. 1mo ago First seen · 750 lines · 18 tokens per session scan A 155890770de4

Subscribe to this mod's changes

career-setup is a skill published in the GitHub repository davekilleen/Dex (505 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 4,712 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.