job-search

job-search is a skill for Claude Code from squerne/open-career-skills. It costs 61 tokens per session (847 once invoked), scanned A, original, MIT.

A job-search workflow that finds current public job postings matching your career profile. It uses public job-board search endpoints and web search, and only reports listings it actually retrieves.

In plain words
What is it for?
Use it to search for roles by profile, skills, domain, and location, review recent postings, and skip companies or jobs already tracked.
Why use it?
It reduces the work of repeating searches across job boards and helps avoid presenting old or made-up vacancies as current. It can also account for applications already recorded in the workspace.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to search for roles by profile, skills, domain, and location, review recent postings, and skip companies or jobs already tracked.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/squerne/open-career-skills/job-search
Install

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.

Any agent
npx skills add squerne/open-career-skills --skill job-search
Clone the repo
git clone --depth 1 https://github.com/squerne/open-career-skills

Made for: Claude Code.

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.

agentmods badge for job-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/squerne/open-career-skills/job-search/github.svg)](https://agentmods.dev/skills/squerne/open-career-skills/job-search)
Your own site
<a href="https://agentmods.dev/skills/squerne/open-career-skills/job-search"><img src="https://agentmods.dev/badge/skills/squerne/open-career-skills/job-search/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.

agentmods 80×15 button for job-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/squerne/open-career-skills/job-search"><img src="https://agentmods.dev/badge/skills/squerne/open-career-skills/job-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 847 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.00847
Opus 5 $0.00030 $0.00424
Sonnet 5 $0.00012 $0.00169
Haiku 4.5 $0.00006 $0.00085

Measured 12d ago against content hash 2165074ca09c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

job-search 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 12d 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.

.claude/skills/job-search/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Job Search (prompt-only)

You find real, current job postings for the user. Iron rule: you only report postings you actually fetched or the user pasted. Never fabricate a listing, never "recall" a job from training data as if it were live, never pad thin results.

Inputs

Read profile/profile.md for target roles, skills, and location; ask only for what's missing (or for a focus override like "/find-jobs data engineering, remote"). Read tracker/applications.md if it exists so you can skip companies+roles already tracked.

Step 1: LinkedIn jobs-guest search (primary, works via plain fetch)

LinkedIn serves public, unauthenticated job search HTML at:

https://www.linkedin.com/jobs-guest/jobs/api/seeMoreJobPostings/search?keywords=<query>&location=<place>&f_TPR=r604800&start=0
  • keywords: role or skill query. location: city/country or Remote. f_TPR=r604800 limits to the last 7 days (r2592000 for 30). f_WT: 1 on-site, 2 remote, 3 hybrid. start: pagination, 10 per page.
  • Fetch 1-3 query variants built from the profile (primary role title, strongest skill, domain keyword). Parse the job cards (title, company, location, date, URL). For the most promising cards, fetch the detail endpoint https://www.linkedin.com/jobs-guest/jobs/api/jobPosting/<jobId> for the full description.
  • Etiquette: keep volume low (a handful of fetches per run, back off on errors); this is for the user's personal search, and automated access sits against LinkedIn's ToS, so say so once in the output footer.

Step 2: Web search + other boards

Run 2-4 web searches with site filters from portals.md (same directory), e.g. site:indeed.com "<role>" <city>, prioritized by the user's market. Fetch promising results for details. Skip anything already in the tracker.

Step 3: Honest degradation

Many boards block automated fetching. When a fetch fails or returns a bot wall, do NOT guess at contents. Instead:

  1. Construct excellent ready-to-open search URLs from portals.md patterns (filled with the profile's roles/location) and give them to the user as clickable links.
  2. Offer: "open these, paste back any posting that looks interesting, and I'll fit-rate it." State plainly which boards were fetched and which only got URLs; coverage transparency beats fake completeness.

Read the full file on GitHub · 44 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 12d ago First seen · 44 lines · 61 tokens per session scan A 2165074ca09c

Subscribe to this mod's changes

job-search is a skill published in the GitHub repository squerne/open-career-skills (23 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 847 once invoked, about $0.0003 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.