claude-linkedin-assistant: Command for Claude Code

.claude/commands/jobs/setup.md

setup is a command for Claude Code from FarzamHejaziK/claude-linkedin-assistant. It costs 0 tokens per session (1,111 once invoked), scanned A, original, MIT.

A setup guide for configuring the job-search assistant, including your resume, LinkedIn connection, and optional Indeed searches.

In plain words
What is it for?
Use it to verify a usable resume, confirm the correct LinkedIn account is open in Chrome, and choose whether Indeed is included.
Why use it?
It checks the required information and connections before a job search begins, reducing setup errors.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is FarzamHejaziK/claude-linkedin-assistant's own configuration. It tells Claude Code how to work on claude-linkedin-assistant itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-linkedin-assistant configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/FarzamHejaziK/claude-linkedin-assistant/main/.claude/commands/jobs/setup.md
Clone the repo
git clone --depth 1 https://github.com/FarzamHejaziK/claude-linkedin-assistant

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 setup

README.md
[![agentmods](https://agentmods.dev/badge/commands/farzamhejazik/claude-linkedin-assistant/setup/github.svg)](https://agentmods.dev/commands/farzamhejazik/claude-linkedin-assistant/setup)
Your own site
<a href="https://agentmods.dev/commands/farzamhejazik/claude-linkedin-assistant/setup"><img src="https://agentmods.dev/badge/commands/farzamhejazik/claude-linkedin-assistant/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.

agentmods 80×15 button for setup

Your own site · 80×15
<a href="https://agentmods.dev/commands/farzamhejazik/claude-linkedin-assistant/setup"><img src="https://agentmods.dev/badge/commands/farzamhejazik/claude-linkedin-assistant/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,111 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 $0.00000 $0.01111
Opus 5 $0.00000 $0.00556
Sonnet 5 $0.00000 $0.00222
Haiku 4.5 $0.00000 $0.00111

Measured 9d ago against content hash 020d4831f05a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 9d 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/commands/jobs/setup.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SETUP (first-run configuration)

/jobs setup walks the user through platform configuration. It runs automatically the first time /jobs find or /jobs daily is invoked without platform config, or manually any time.


Step 1 — Resume check

List resumes/. Filter out README.md and search_profile.md.

  • Zero resume files → follow the same warm prompt from jobs.md Step 0A. Wait for the user to provide one before continuing.
  • Resume found → extract name, current title, and at least one skill. Hold the name for Step 2.

Step 2 — Chrome + LinkedIn verification

Run the same Chrome + LinkedIn check from jobs.md Step 0B:

  1. Verify Chrome extension is connected.
  2. Navigate to https://www.linkedin.com/in/me/.
  3. Confirm the signed-in profile name matches the resume name.
  4. Print: ✓ LinkedIn: <name>

If any check fails, stop with the same error messages as jobs.md Step 0.

For the Chrome-extension failure case, use the full recovery checklist from jobs.md Step 0B so first-time users know how to install/enable the extension and retry setup.


Step 3 — Indeed opt-in

Ask:

Do you want to include Indeed in your job searches? It adds Indeed as another source alongside LinkedIn and WebSearch. Requires being signed into indeed.com in this Chrome browser. (yes / no / later)

User says no or later

  • Read resumes/search_profile.md if it exists (to preserve existing content).
  • Add or update the ## Platforms section:
    ## Platforms
    - LinkedIn: yes
    - Indeed: no
    
  • Add or update the ## Indeed section:
    ## Indeed
    - Discovery: disabled
    
  • Print: Indeed skipped. You can enable it later with /jobs indeed-setup.
  • Skip to Step 5.

User says yes

  1. Navigate to https://www.indeed.com/ in Chrome.
  2. Read the page.
  3. Signed in (user's name/avatar visible, account menu present):
    • Print: ✓ Indeed: signed in
    • Write Indeed: yes and Discovery: enabled to search profile (see state format below).
    • Continue to Step 4.
  4. Not signed in (shows "Sign in" / login page):
    • Tell the user: "Not signed into Indeed. Please sign in at indeed.com in this browser, then tell me 'done'."
    • Wait for confirmation.
    • Re-navigate and re-check.
    • If now signed in → write state, continue to Step 4.
    • If still not signed in → "Still not seeing a signed-in state. Try again, or say 'skip' to disable Indeed for now."
  5. CAPTCHA / blocked / blank page:
    • Print: "Indeed is blocking automation right now. I'll mark it as skipped. You can enable it later with /jobs indeed-setup."
    • Write Discovery: disabled and Profile optimization: blocked.
    • Skip to Step 5.

Read the full file on GitHub · 134 lines

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. 9d ago First seen · 134 lines · 0 tokens per session scan A 020d4831f05a

Subscribe to this mod's changes

setup is a command published in the GitHub repository FarzamHejaziK/claude-linkedin-assistant (213 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,111 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.