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 Remotivated/job-hunt-skills --skill get-startedgit clone --depth 1 https://github.com/Remotivated/job-hunt-skillsWrote 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/remotivated/job-hunt-skills/get-started)<a href="https://agentmods.dev/skills/remotivated/job-hunt-skills/get-started"><img src="https://agentmods.dev/badge/skills/remotivated/job-hunt-skills/get-started/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/remotivated/job-hunt-skills/get-started"><img src="https://agentmods.dev/badge/skills/remotivated/job-hunt-skills/get-started.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 | $0.00132 | $0.03335 |
| Opus 5.5 | $0.00053 | $0.01334 |
| Sonnet 5.5 | $0.00026 | $0.00667 |
| Haiku 4.5 | $0.00013 | $0.00333 |
Grade A, and why
get-started 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 11d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The onboarding wrapper for Job Hunt Skills. A first-time user should reach real value fast, then be invited into the deeper build — not marched through a 20-minute interview before seeing anything. This skill offers two doors: a fast path (paste a resume + a posting, get a tailored draft and honest audit in minutes) and the deep build (resume-builder's full source-document interview). Lead with the fast path; the deep build is where the compounding value lives, offered once the user has felt the first win.
Choosing the door
After orientation (step 1), route on what the user has:
- Has an existing resume/CV or LinkedIn profile → fast path (step 2). This is the default; most first-timers arrive with a resume.
- Pasted a resume and a job posting already → go straight into the fast path with that material.
- No resume yet, or explicitly wants to build the source document properly → deep build (step 4).
- Asks whether a specific posting is worth pursuing, rather than for tailoring → hand off to
opportunity-evaluator, which gives an in-chat read first and saves nothing until the user decides.
The fast path runs in-chat first and only touches disk once the user asks to save — so the workspace preflight (step 3) happens at save time, not before the user has seen anything. The deep build confirms the workspace up front because its whole output is files.
Workflow
1. Orient the user — BEFORE any questions, forms, or input gathering
Give a short orientation in plain language before asking for any information. You're talking to a jobseeker, not a developer. Keep it to two or three sentences, then offer the fast path. Do not open with the long interview.
This step is load-bearing: hand over a long input form first and explain afterwards, and the form is already filled by the time the user knows what is happening or that fields can be skipped. Orientation MUST land first, and the user MUST choose a door before any structured prompt — single question, multi-field form, or batched interview — appears.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago Changed · +1 lines a438ce60f6b3
- 25d ago Changed 1b5de3f4d619
- 1mo ago First seen · 159 lines · 132 tokens per session scan A 1dbba79d0e70
get-started is a skill published in the GitHub repository Remotivated/job-hunt-skills (16 stars, last pushed 3d ago), licensed MIT. It adds 132 tokens to every session and 3,335 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
career-compass
Use for any job-search or career task, even a short casual ask that never names Career Compass. Triggers include a pasted job posting or JD, a résumé or CV, "should I apply", "do I fit this", "help me apply", tailoring a résumé or cover letter, a LinkedIn headline or About section, tracking applications, a recruiter…
cv-resume-builder
Optimize resumes and CVs for impact, ATS compatibility, and audience targeting. Supports multiple formats (chronological, functional, hybrid), accomplishment framing (STAR/XYZ), and tailoring for specific roles. Triggers on resume review, CV update, job application prep, or career document requests.
today
See what needs attention in your job search today, such as follow-ups due, upcoming interviews, and stale applications, in priority order.
feedback
Tell Career Compass's maker what it got wrong. Turns what happened into a short report with your personal details taken out, shows you every word, and gives you a link to send it. Nothing is sent unless you send it.
debrief
Debrief an interview while it's fresh. Get what landed, what to sharpen, a thank-you note per interviewer from your own notes, and the next step.
week
Review your job-search week. What moved, stalled or closed, the patterns in your notes, your pace against your goal, and one focus for next week.