job-discovery

job-discovery is a skill for Claude Code, Codex from sayantan94/AppliedIn. It costs 50 tokens per session (344 once invoked), scanned A, original, MIT.

A job-search tool that checks a watchlist of companies for new openings, including listings from recruiting systems and custom careers pages. It filters and queues postings that match the candidate’s stated preferences.

In plain words
What is it for?
Use it to discover and poll new jobs, remove already-seen listings, queue matching openings, and report companies whose job pages could not be checked.
Why use it?
It reduces the need to visit many career pages repeatedly and avoids adding the same posting twice. More detailed matching happens later in the application process.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to discover and poll new jobs, remove already-seen listings, queue matching openings, and report companies whose job pages could not be checked.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sayantan94/appliedin/job-discovery
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 sayantan94/AppliedIn --skill job-discovery
Clone the repo
git clone --depth 1 https://github.com/sayantan94/AppliedIn

Made for: Claude Code, Codex.

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-discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/sayantan94/appliedin/job-discovery/github.svg)](https://agentmods.dev/skills/sayantan94/appliedin/job-discovery)
Your own site
<a href="https://agentmods.dev/skills/sayantan94/appliedin/job-discovery"><img src="https://agentmods.dev/badge/skills/sayantan94/appliedin/job-discovery/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-discovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/sayantan94/appliedin/job-discovery"><img src="https://agentmods.dev/badge/skills/sayantan94/appliedin/job-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 344 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 $0.00050 $0.00344
Opus 5 $0.00025 $0.00172
Sonnet 5 $0.00010 $0.00069
Haiku 4.5 $0.00005 $0.00034

Measured 10d ago against content hash 0bf2b2df6fa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

job-discovery 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 10d 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.

src/agent/skills/job-discovery/SKILL.md · 35 lines

What it actually says

Job discovery

Find every new, matching job across the watchlist and enqueue it for the application pipeline. Be exhaustive — a missed posting is a missed opportunity.

Instructions

Step 1: Get the watchlist

Call list_companies. It returns each company with its careers URL and whether it's a feed or a crawl target.

Step 2: Discover each company

Call discover_company(name) for every company in the list — do not skip any. It resolves the company's ATS from the careers URL, fetches the feed (or crawls a custom page), filters to the candidate's preferences, dedups against what's already been seen, and enqueues the new matches. It returns how many new jobs it enqueued.

Step 3: Report

Sum the enqueued counts and list any company that returned an error, so the watchlist can be fixed.

Rules

  • Discovery is idempotent: a posting already seen is skipped (deterministic dedup). Running twice never double-enqueues — safe to run on a schedule.
  • Only postings passing the stage-1 preference filter are enqueued; the deeper LLM match-score happens later, in the pipeline's scorer.
  • If a company errors (unreachable page, changed ATS), report it and move on — one bad company must not stop discovery.
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. 10d ago First seen · 35 lines · 50 tokens per session scan A 0bf2b2df6fa0

Subscribe to this mod's changes

job-discovery is a skill published in the GitHub repository sayantan94/AppliedIn (7 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 344 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 2026-08-31.