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.
npx skills add davekilleen/Dex --skill career-coachgit clone --depth 1 https://github.com/davekilleen/DexWrote 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.
[](https://agentmods.dev/skills/davekilleen/dex/career-coach)<a href="https://agentmods.dev/skills/davekilleen/dex/career-coach"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/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.
<a href="https://agentmods.dev/skills/davekilleen/dex/career-coach"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/career-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.08262 |
| Opus 5.5 | $0.00010 | $0.03305 |
| Sonnet 5.5 | $0.00005 | $0.01652 |
| Haiku 4.5 | $0.00002 | $0.00826 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 1,298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execution mode
Run inline in the current conversation by default, so this work can see what the user has already discussed, decided, or settled this session. Do not fork merely because this skill was selected. Only run in the background when the user explicitly asks for a background run or the host has already obtained a specific background-work approval for this run.
Purpose
Your personal career development coach. Brain dump about your work, reflect on challenges, and get coaching that adapts to your role and career level. Generates reports, reflections, self-reviews, and promotion assessments based on accumulated evidence.
Prerequisites
Run /career-setup first to establish baseline (job description, career ladder, latest review, growth goals).
Career MCP Integration
This command uses Career MCP tools for efficient data aggregation:
scan_evidence()- Aggregates all career evidence files with structured parsingparse_ladder()- Extracts competency requirements from career ladderanalyze_coverage()- Maps evidence to competencies with coverage statisticstimeline_analysis()- Tracks evidence trends and growth velocity
How it works: MCP tools provide structured data → LLM interprets and coaches. This makes assessments faster, more consistent, and enables trend tracking over time.
Before interpreting any result, verify that the Career room is enabled and record
which Career and Work MCP tools are available, unavailable, or unknown. Preserve
the source identifier or path, source date, and retrieval as-of date/time for
each claim. A result without provenance is unknown; contradictory sources must
be shown as contradictory and resolved with the user, not silently merged. Never
invent absent evidence, dates, metrics, intent, or outcomes.
Usage
/career-coach [optional initial brain dump]
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.
- 1mo ago Changed · -3 lines 0a7b6ed51974
- 1mo ago First seen · 1,301 lines · 24 tokens per session scan A ff1997a5eb40
career-coach is a skill published in the GitHub repository davekilleen/Dex (508 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 8,262 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.
Other skills, from other repositories
meeting-notes
Use when the user asks to capture, structure, or summarize meeting notes / call notes / 1:1 discussion / standup notes. Produces a standard template with attendees, agenda, decisions, action items (owner + deadline), and open questions.
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
schedule
Reminders, automations, and recurring page, dashboard, or status monitoring (cron, RRULE, or fire-at).
inbox-cleanup
Run a high-recall, multi-pass email inbox cleanup. Pattern-based subject queries catch 25x more archivable email than sender scans alone. Includes urgency triage, classification signals, and post-cleanup filter setup.
inbox-management
Ongoing Gmail inbox management via scheduled runs. Archives known noise, flags urgent items, drafts replies in-thread (never auto-sends), and catches stale follow-ups. Empty polls spend no model tokens. Starts in flag-only mode.
notifications
Send notifications through the unified notification router.