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/add.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/add)<a href="https://agentmods.dev/commands/farzamhejazik/claude-linkedin-assistant/add"><img src="https://agentmods.dev/badge/commands/farzamhejazik/claude-linkedin-assistant/add/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/add"><img src="https://agentmods.dev/badge/commands/farzamhejazik/claude-linkedin-assistant/add.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 | $0.00789 |
| Opus 5 | $0.00000 | $0.00394 |
| Sonnet 5 | $0.00000 | $0.00158 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
add 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADD (new job)
The agent's job is to find the listing from minimal input — not to interrogate the user. Default behavior: take whatever the user gave you (could be just a URL, just "Company + Role", or just "Company"), and fill in the rest yourself via Chrome + WebSearch.
Step 1 — Resolve to a job URL
| What the user gave | What the agent does |
|---|---|
| Just a URL | Navigate to it. Scrape Company, Role, Location, Type, Salary from the posting. |
| Company + Role | Run WebSearch for "<Company>" "<Role>" jobs site:linkedin.com OR site:greenhouse.io OR site:ashbyhq.com 2026. Pick the most recent matching listing. Open it in Chrome and scrape the same fields. If multiple plausible matches (>1 active listing for that title at that company), pick the most recently posted; print a one-line note "Multiple matches, picked most recent: ". |
| Just Company | Run WebSearch for "<Company>" careers OR jobs 2026 to get the careers page. Navigate Chrome there. List the open roles, ask the user "Which role?" with a numbered list. Then continue as in row 2. |
If the search returns nothing usable for the Company+Role combo (no live listing, only old/closed posts), tell the user clearly: "Couldn't find a live listing for <Role> at <Company>. Paste the job URL and I'll add it." Wait for the URL, then continue.
Step 2 — Auto-fill the row
From the resolved listing, extract and fill:
- Company, Role, URL, Location, Type, Salary — straight from the page.
- Priority — default to
MEDIUM. Bump toHIGHif any of: title is a strong match for the user's most-recent role title fromresumes/, the company is in the user'ssearch_profile.mdinterests, or the salary is at/above the profile's floor. Drop toLOWif the role is borderline-relevant. - Notes — optional, leave blank unless the user provided something.
Do NOT ask the user for any of these. If a field can't be scraped (e.g. salary not shown), leave it blank.
Auto-determine Referral Needed
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 · 43 lines · 0 tokens per session scan A f0ebf48f20e6
add 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 789 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
triage
Triage Linear issue with comprehensive analysis.
help
Explain Ralph Wiggum technique and available commands.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
vitaecontext-vitaegraph
Create, validate, index, or use a private VitaeGraph.
terse
Switch reply compression level — /terse [lite|full|ultra|off]. Complements RTK (input savings) with output-side savings.
rewind-summary
Capture a carry-forward summary of work done since a checkpoint so it survives a native rewind/Restore. Run before rewinding.