Career Ops
AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.
Last verified:
What is Career Ops?
Career Ops — areer-ops is an open-source AI-powered job search system that runs locally on your machine inside any AI coding CLI—Claude Code, Codex, OpenCode, Gemini CLI, Qwen, or GitHub Copilot. It evaluates job listings against your CV using a six-dimension rubric scoring 1.0–5.0, generates ATS-optimized PDF resumes tailored per role, drafts answers to open-ended application questions on Greenhouse, Ashby and Lever forms, scans 150+ company portals zero-token, and tracks the pipeline in a Go-based terminal dashboard. Everything lives on your machine: no cloud, no telemetry, no account. MIT-licensed and free forever; the only cost is whichever AI coding CLI you already pay for.
Built by Santiago Fernández de Valderrama after a real 2026 job search of 740 listings, 66 applications, 12 interviews, and one offer (Head of Applied AI at Zinkee), career-ops is designed for candidates running an active, structured job search. It works best for people who have a CV they are happy with and want to tailor per application without rewriting it manually, who are tracking multiple applications and want a single source of truth instead of a sprawling spreadsheet, and who want to apply only to roles that actually fit rather than everything vaguely relevant.
Key features include: rubric-guided LLM evaluation across six dimensions (match, north-star alignment, comp, cultural signals, red flags, global fit); PDF resume generation citing specific CV lines; /career-ops apply that drafts every answer for Greenhouse/Ashby/Lever forms; /career-ops scan checking 150+ career pages; /career-ops tracker for pipeline visibility; /career-ops contacto finding hiring managers on LinkedIn; and a Go-based TUI dashboard for browsing reports. The full scoring methodology is published, and the project grows through community contributions.
career-ops is for technical job seekers, applied AI professionals, engineers, product managers, and anyone comfortable running commands in a terminal who wants A
Career Ops pricing
Pricing model: Freemium
career-ops is permanently free, MIT-licensed forever, and community-funded. There is no paid tier, no waitlist, no account, no telemetry, and no premium features. You clone the repo, configure your profile, and run the system locally with whichever AI coding CLI you already use. The only recurring cost is your AI CLI subscription (typical job search runs on Claude Pro at $20/month, but you choose the CLI). Sustainability comes from voluntary community patronage via GitHub Sponsors with nine tiers from $1 to $1,000 per month. Individual tiers ($1-$250) are identical statements of support with no gated perks. Corporate tiers ($500 Corporate Supporter, $1,000 Ecosystem Partner) add logo placement on the README and sustain page, acknowledgment in release notes, and the $1,000 tier includes invitation to private architectural discussions—no premium features or roadmap influence for any tier.
Career Ops pros
- Permanently free, MIT-licensed forever with no paid tier
- Runs locally on your machine—no cloud, no telemetry, no account
- Your CV and application data never leave your machine unless you push them
- Works with any AI coding CLI: Claude Code, Codex, OpenCode, Gemini CLI, Qwen, GitHub Copilot
- Six-dimension rubric scoring 1.0–5.0 with citations to specific CV lines and JD requirements
- Generates ATS-optimized PDF resumes tailored per role automatically
- Drafts tailored answers for Greenhouse, Ashby, and Lever application forms
- Scans 150+ company portals (Greenhouse, Ashby, Lever) with zero API tokens
- Go-based terminal dashboard (TUI) for browsing and filtering all reports
- 4.0/5.0 apply threshold prevents spray-and-pray job applications
- Full scoring methodology published transparently at career-ops.org/methodology
- 47K+ GitHub stars with 9K+ forks and active community contributions
- /career-ops contacto finds hiring managers on LinkedIn and drafts outreach messages
- /career-ops tracker shows status of every role in your pipeline
- No auto-apply—every submission is your manual decision with agent reasoning visible
Career Ops cons
- Requires 15 minutes setup time: cloning repo, configuring YAML, adding CV in markdown
- Only suitable for active structured job searches, not casual browsing with 1-2 applications
- Requires comfort running commands in a terminal
- Does not apply to jobs for you—must manually copy answers and submit forms yourself
- Not a resume builder—you must bring your own CV already written
- No LinkedIn scraping feature shipped yet (issue #238 approved but not implemented)
- Token cost depends on which AI CLI you use; metered API keys can get expensive
- No cloud storage—local-only execution via Ollama still pending (PR #561)
Frequently asked questions about Career Ops
How does career-ops score job listings?
career-ops uses a rubric-guided LLM evaluation across six dimensions—match, north-star alignment, comp, cultural signals, red flags, and global fit—producing a 1.0–5.0 score with citations to specific CV lines and JD requirements. Anything below 4.0 the agent recommends against applying. There is no closed-form weighting formula; the global score is the LLM's judgement given the rubric. The full rubric is published at career-ops.org/methodology.
Is career-ops free? What is the business model?
career-ops is permanently free, MIT-licensed, and community-funded. There is no paid tier, no waitlist, no account, no telemetry, and no premium features. You clone the repo, configure your profile, and run locally with your AI coding CLI. Sustainability comes from voluntary community patronage via GitHub Sponsors—not from premium tiers, paid features, or data. The maintainer has other paid work for income; sponsorship enables deeper focus on the project.
Who built career-ops and why?
career-ops was built by Santiago Fernández de Valderrama, an Applied AI Operator with 16+ years building products and currently Head of Applied AI at Zinkee. He created it in early 2026 to manage his own AI-era job search—740 listings evaluated, one Head of AI role landed—and open-sourced it under MIT once he no longer needed it, so anyone running a structured job search can use the same system for free.
Is career-ops a Claude Code skill or a standalone tool?
career-ops is CLI-agnostic. It works with Claude Code, Codex, OpenCode, Gemini CLI, Qwen, and Copilot—whichever AI coding agent you already pay for. The skill files (modes/) live in the repo as plain markdown prompts; any agent that supports skill loading can invoke them. There is no Anthropic-specific dependency. Claude Code is the most common runtime because of its skill loader, but the same modes run unchanged in other CLIs.
How is career-ops different from other AI job search tools like Jobscan or Teal?
Most AI job search tools—Jobscan, Teal, Huntr, autoapply.ai—are cloud SaaS products that upload your resume and job data to their servers, charge $20–80/month, and keep their matching algorithm closed. career-ops is the inverse: open source, MIT-licensed, runs locally on your machine through whichever AI CLI you already use, and publishes the full evaluation rubric. The only recurring cost is your AI CLI subscription.
What AI tools does career-ops work with?
Claude Code (primary), Codex (OpenAI), OpenCode, Gemini CLI (Google), Qwen, and GitHub Copilot. The same mode files run on all six. Each user picks the CLI that fits their existing subscription and cost preferences—career-ops never locks you to one provider. A typical job search runs on Claude Pro at $20/month, but the choice is yours.
What data does career-ops collect from users?
career-ops itself collects nothing. It is local code that runs on your machine. The only data leaving your computer is whatever your configured AI CLI sends to its provider—and that subset is whatever pieces of your CV and the public job postings you choose to evaluate. Local-only execution via Ollama is in flight (PR #561).
Does career-ops apply to jobs for me automatically?
No. career-ops evaluates, scores, generates tailored answers and PDFs, and tracks—but every submission is your decision. The system drafts answers for Greenhouse/Ashby/Lever forms and hands them back paste-ready, but you edit, you submit. The assistant never clicks Submit for you. After you submit, you confirm in the chat so career-ops updates the tracker status.
What is the 4.0/5.0 threshold and how should I use scores?
Every evaluation produces a global score 1.0–5.0. The recommendation tier is fixed: 4.5+ is a strong match (apply immediately), 4.0–4.4 is a good match (worth applying), 3.5–3.9 is decent but not ideal (apply only with specific reason), below 3.5 is recommended against applying. 4.0 is the apply/don't-apply line. The 3.5–3.9 band is an explicit override-only zone—the agent says so, you decide.
What job portals does career-ops scan?
career-ops scans 150+ company portals across Greenhouse, Ashby, and Lever via their public APIs with zero tokens and no scraping. For other portals it can use Playwright through a configured AI CLI. It does not integrate with employer-side ATS, does not scrape LinkedIn (issue #238), and does not use anti-bot fingerprint masking (PR #235 rejected by design). Run /career-ops scan to get a ranked list back in minutes.