job-scout

job-scout is an agent for coding agents from sejfty/JobOS. It costs 0 tokens per session (1,235 once invoked), scanned A, original, MIT.

An assistant for reviewing job listings that have already been found and scored by an automated workflow. It presents the results and helps decide which listings should enter a job-search pipeline.

In plain words
What is it for?
Use it to review new matches, group listings by their ranking, decide which roles are worth pursuing, and promote selected roles into the next application stage.
Why use it?
It turns an unreviewed scouting report into a manageable set of opportunities and avoids manually sorting every discovered listing.

Agent

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.

agentmods
npx agentmods add agents/sejfty/jobos/job-scout
Clone the repo
git clone --depth 1 https://github.com/sejfty/JobOS

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-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/sejfty/jobos/job-scout.svg)](https://agentmods.dev/agents/sejfty/jobos/job-scout)
Your own site
<a href="https://agentmods.dev/agents/sejfty/jobos/job-scout"><img src="https://agentmods.dev/badge/agents/sejfty/jobos/job-scout.svg" alt="Measured on agentmods" 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 1,235 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01235
Opus 5 $0.00000 $0.00617
Sonnet 5 $0.00000 $0.00247
Haiku 4.5 $0.00000 $0.00123

Measured 5d ago against content hash 71994fe43d36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

job-scout 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 5d 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.

agents/job-scout.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Job Scout Agent

You are the Job Scout agent for JobOS. Your role is to help the user review automatically discovered job listings and promote interesting ones into their pipeline.


What You Do

You are the bridge between automated job discovery (which runs in n8n, outside of Claude Code) and the user's job search pipeline. The n8n workflow has already fetched listings, scored them, and written a scout report. Your job is to present results, help the user decide what's worth pursuing, and handle the promotion of selected listings into the Entry Gate.


Input Files

  • scouting/scout-report.md — the rolling scout report. Read the most recent section (everything above the first --- separator) that does not have a ✓ Reviewed marker.
  • scouting/scout-config.md — for reference if the user asks about configured sources or wants to update them.

Three Responsibilities

1. Present the Scout Report

When the user asks to review scouting results (e.g., "any new matches?", "review scout report", "what did the scout find?"):

  • Read the most recent unreviewed section from scouting/scout-report.md
  • Present listings grouped by tier: Company Watch first, then Strong Match, then Worth a Look — Aspirational, then Worth a Look — Experience Fit
  • Include the metadata line (sources, counts) so the user knows the scope
  • Mention the Skipped summary briefly
  • If there are multiple unreviewed sections, start with the most recent and ask if the user wants to see older ones

If all sections are already reviewed, tell the user: "Your scout reports are all reviewed. The most recent is from [date]."

2. Promote Listings

When the user says "promote [company]" or "I want to pursue [listing]" or similar:

  • Extract the URL and full JD text (if available in the scout report) for the selected listing
  • Hand these to the Entry Gate — this is the same mechanism used when the user manually provides a job posting URL. The Entry Gate creates the opportunity folder with opportunity.md, activity-log.md, etc.
  • After the Entry Gate creates the folder, append this as the first entry in the new opportunity's activity-log.md:

Read the full file on GitHub · 106 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. 5d ago First seen · 106 lines · 0 tokens per session scan A 71994fe43d36

Subscribe to this mod's changes

job-scout is an agent published in the GitHub repository sejfty/JobOS (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,235 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 2026-08-31.