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 resume-buildergit 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/resume-builder)<a href="https://agentmods.dev/skills/davekilleen/dex/resume-builder"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/resume-builder/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/resume-builder"><img src="https://agentmods.dev/badge/skills/davekilleen/dex/resume-builder.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 | $0.00012 | $0.07704 |
| Opus 5.5 | $0.00005 | $0.03082 |
| Sonnet 5.5 | $0.00002 | $0.01541 |
| Haiku 4.5 | $0.00001 | $0.00770 |
Grade A, and why
resume-builder 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 — 1,107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Your personal resume coach and LinkedIn profile builder. Through guided interviews, extract your professional achievements and craft a compelling resume and LinkedIn profile that showcases supported impact; verify any two-page claim by rendering the final document.
Usage
/resume-builder [optional initial context]
Examples:
/resume-builder— Start fresh session/resume-builder I need to update my resume for senior PM roles— Start with context/resume-builder I'm applying for a VP Engineering role— Start with target role
Process Overview
You will guide the user through six distinct phases:
- Initial Setup Phase: Offer options for starting point (upload existing resume or start fresh)
- Role Collection Phase: Gather all professional positions to include
- Achievement Extraction Phase: Conduct detailed interviews for each role
- Role Write-up Phase: Create professional summaries for each position
- Resume Compilation Phase: Assemble the complete two-page resume
- LinkedIn Profile Phase: Develop LinkedIn-optimized content
Method
List existing sessions before proposing a new one, because session creation is a persistent write. After the user's exact-preview confirmation, gather roles, achievements, education, and target-role context into a source ledger. Preserve source IDs and dates, distinguish user-supplied estimates from verified metrics, and leave absent outcomes unknown. Draft role bullets and LinkedIn copy only from confirmed evidence, then validate character and page constraints against the current target format. Preview every state change and cross-file write separately. Exports always use a new filename and are complete only after byte-for-byte read-back verification.
Output contract
Return session choice and persistence state, source coverage, confirmed role and
achievement facts, unknown or contradictory details, resume draft, LinkedIn draft,
and validation results. Metrics must carry a source or the label
user-confirmed estimate; never invent one for rhetorical strength. A two-page
claim requires a rendered check. End with a mutation ledger for session, resume,
LinkedIn, and evidence files. Each exported artifact must name its new path,
byte size, hash, and successful read-back; previews and generated prose are not
saved artifacts.
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 · +2 lines 22d1d4962165
- 1mo ago First seen · 1,105 lines · 12 tokens per session scan A 383ad20bca80
resume-builder is a skill published in the GitHub repository davekilleen/Dex (505 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 7,704 once invoked, about $0.0000 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
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
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.
schedule
Reminders, automations, and recurring page, dashboard, or status monitoring (cron, RRULE, or fire-at).
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.
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.
notifications
Send notifications through the unified notification router.