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.
npx skills add sayantan94/AppliedIn --skill job-discoverygit clone --depth 1 https://github.com/sayantan94/AppliedInWrote 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/skills/sayantan94/appliedin/job-discovery)<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.
<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>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 | $0.00050 | $0.00344 |
| Opus 5 | $0.00025 | $0.00172 |
| Sonnet 5 | $0.00010 | $0.00069 |
| Haiku 4.5 | $0.00005 | $0.00034 |
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.
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.
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.
- 10d ago First seen · 35 lines · 50 tokens per session scan A 0bf2b2df6fa0
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.