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.
git clone --depth 1 https://github.com/andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-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.
[](https://agentmods.dev/commands/andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-/setup)<a href="https://agentmods.dev/commands/andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-/setup"><img src="https://agentmods.dev/badge/commands/andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-/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.
<a href="https://agentmods.dev/commands/andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-/setup"><img src="https://agentmods.dev/badge/commands/andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-/setup.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 | $0.00028 | $0.01185 |
| Opus 5 | $0.00014 | $0.00593 |
| Sonnet 5 | $0.00006 | $0.00237 |
| Haiku 4.5 | $0.00003 | $0.00119 |
Grade A, and why
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 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set Up Your Profile
Walk the user through creating their job search profile. Conversational, friendly, zero jargon. This is the first thing a new user does.
Step 0: Check Existing
Read data/profile.yml. If it exists and no --reset flag:
"You're already set up! Here's a quick summary of your profile:
{Name} — {Current title} at {Company} Looking for: {Target role}
Want to update it? Say 'setup --reset' to start fresh, or tell me what to change and I'll update just that part."
If --reset flag or file doesn't exist, continue to Step 1.
Step 1: Welcome
"Let's set up your job search profile. This helps me evaluate jobs, tailor resumes, and write messages that actually sound like you.
Fastest way: Paste your resume below (text or PDF content) and I'll pull everything from it automatically.
Or I can ask you a few questions instead. What do you prefer?"
Step 2A: Resume Ingestion (preferred path)
If the user pastes resume content:
-
Parse the resume into structured data:
- Name, contact info, LinkedIn URL
- Work history (each role: title, company, dates, bullet points)
- Education (degree, school, year)
- Skills (extract all mentioned skills and tools)
- Certifications/licenses (if any)
- Projects or portfolio items (if listed)
-
Save the raw resume text to
data/resume.mdas a reference document. -
Ask follow-up questions for fields NOT in the resume:
- "What kind of role are you looking for next?"
- "Where are you willing to work? (Remote, specific city, flexible)"
- "What's your target salary range? (Skip if you'd rather not say)"
- "Anything else I should know? Career change, gap to explain, special situation?"
-
Continue to Step 3.
Step 2B: Conversational Collection (fallback)
If the user prefers questions, ask these one at a time. Wait for each answer.
- "What's your name?"
- "What do you do right now? (Job title and company, or 'between jobs')"
- "Walk me through your last 2-3 roles briefly. For each: title, company, how long, and one or two things you accomplished."
- "What kind of role are you looking for? (Job title, industry)"
- "Where are you willing to work? (City, remote, hybrid, relocate)"
- "How many years of work experience total?"
- "What are your strongest skills? (Top 5-10)"
- "Any certifications or licenses? (Skip if none)"
- "What's your salary range? (Target and minimum, or skip)"
- "Got a LinkedIn profile URL?"
- "Anything else? (Career change, gap, special circumstances, portfolio)"
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 First seen · 140 lines · 28 tokens per session scan A c184894dde6b
setup is a command published in the GitHub repository andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2- (490 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 1,185 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
job-hunt
A command for searching for jobs each day and tracking the application process. The input also refers to candidate details and companies already contacted.
setup
A guided first-configuration command for a newly cloned repository. The provided description says it fills in local settings by talking with the user, but does not list those settings.
apply
A command for a job-application workflow that recommends a CV version, generates a cover letter, and answers tailored application questions.
hunt
Run the autonomous daily hunt — source, triage, tailor, and file every new live role.
dashboard
Build a shareable HTML dashboard of your hunt — funnel, status, categories, recruiter scores — from the tracker.
tailor
Tailor an ATS-safe CV to one job description from the master profile.