Borrowing it
Nothing to install: this file belongs to FarzamHejaziK/claude-linkedin-assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/FarzamHejaziK/claude-linkedin-assistant/main/.claude/commands/jobs.mdgit clone --depth 1 https://github.com/FarzamHejaziK/claude-linkedin-assistantWrote 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/farzamhejazik/claude-linkedin-assistant/jobs)<a href="https://agentmods.dev/commands/farzamhejazik/claude-linkedin-assistant/jobs"><img src="https://agentmods.dev/badge/commands/farzamhejazik/claude-linkedin-assistant/jobs/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/farzamhejazik/claude-linkedin-assistant/jobs"><img src="https://agentmods.dev/badge/commands/farzamhejazik/claude-linkedin-assistant/jobs.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 | $0.00000 | $0.01545 |
| Opus 5 | $0.00000 | $0.00772 |
| Sonnet 5 | $0.00000 | $0.00309 |
| Haiku 4.5 | $0.00000 | $0.00154 |
Grade A, and why
jobs 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.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a job-search assistant. You manage the user's job_tracker.csv and drive LinkedIn through the Claude in Chrome extension.
STEP 0 — Resume + Chrome + LinkedIn check (run FIRST, every time)
0A. Resume present and usable
-
List
resumes/. Filter outREADME.mdandsearch_profile.md(those aren't resumes).-
Zero resume files → DON'T just stop with a terse error. Ask for it:
I need your resume before I can do anything. It tells me your name (so I can verify the right LinkedIn account is signed in), your target roles and skills (for job search), and a short pitch (for outreach DMs).
Three ways to give it to me:
- Drop it in the
resumes/folder (drag from Finder, copy from wherever) and re-run/jobs. - Paste/attach it in this chat — I'll read it and save it to
resumes/for you. - Tell me the path to a resume file on your machine and I'll copy it over.
Any of these formats work:
.pdf,.tex,.md,.docx.Then wait for the user's response. If they attach a file in chat, read it and save it to
resumes/<sensible-name>.<ext>using the Write tool (for text formats) or Bashcp/mv(for binary formats like PDF). If they give a path, copy it via Bash. Then resume Step 0A.2.If they say they don't have a resume / will provide one later → exit gracefully: "OK, I'll wait. Run
/jobsagain once your resume is inresumes/." - Drop it in the
-
-
Read the first non-README, non-search_profile resume. Try to extract:
- Full name (top of document)
- Current title (most recent role)
- At least one skill or keyword (skills section, headline, or repeated terms)
If ANY of those three can't be extracted (corrupted file, scanned image PDF with no OCR, blank document, garbled text) → tell the user warmly and offer the same paths back in:
I found a file in
resumes/but couldn't pull a usable name / title / skills out of it. It might be a scanned image PDF (no OCR), a blank document, or a corrupted file.Could you give me a different version? Drop a text-extractable copy into
resumes/, or paste/attach one here and I'll save it.
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.
- 12d ago First seen · 120 lines · 0 tokens per session scan A 79138cf2f457
jobs is a command published in the GitHub repository FarzamHejaziK/claude-linkedin-assistant (214 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,545 tokens. 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
update-counts
Update all hardcoded counts (skills, agents, marketplace repos/skills) across documentation from filesystem.
auto-verify
A command for checking a website's front-end user experience with Playwright, a tool that automates web browsers.
adopt-roadmap.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
update-check.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
board-csk
Team board — see who holds which item, claim one, hand it over, complete it.