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 tmargolis/career-navigator --skill search-jobsgit clone --depth 1 https://github.com/tmargolis/career-navigatorWrote 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/tmargolis/career-navigator/search-jobs)<a href="https://agentmods.dev/skills/tmargolis/career-navigator/search-jobs"><img src="https://agentmods.dev/badge/skills/tmargolis/career-navigator/search-jobs/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/tmargolis/career-navigator/search-jobs"><img src="https://agentmods.dev/badge/skills/tmargolis/career-navigator/search-jobs.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 | $0.00041 | $0.02830 |
| Opus 5 | $0.00020 | $0.01415 |
| Sonnet 5 | $0.00008 | $0.00566 |
| Haiku 4.5 | $0.00004 | $0.00283 |
Grade A, and why
search-jobs 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 12d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search and rank job listings that match the user's profile using a connector-first strategy.
Source model and normalization
Use a hybrid source model in this order:
- Connector-native MCP (preferred) for any available source (Indeed first in current implementation).
- Browser-assisted capture (Claude in Chrome / computer use) only when MCP is missing or the flow is browser-only.
- Assisted-manual ingestion as guaranteed fallback.
Normalize all listings into this schema before ranking:
title(required)company(required)location(required)apply_url(required)source(required; examples:indeed,illinoisjoblink,wellfound,company_direct,ats_greenhouse)retrieval_mode(required;mcp|browser|manual)salary(optional, raw text if no structured range)posted_date(optional)close_date(optional; common on public-sector postings)employment_type(optional)job_id_or_requisition(optional but preferred for dedupe)raw_description(optional but preferred for stronger scoring)
If required fields are missing, ask for only the missing fields before ranking.
Preflight (connector-first)
Live path: If search_jobs and get_job_details are available, use them as the primary lane and follow §1–§5 below.
No Indeed MCP in this session: Do not invent tool results. Do both of the following:
-
Explain how to enable live search on Claude Desktop: Customize → Connectors → Indeed → Connect → complete Grant access to Indeed in the browser (Indeed OAuth on secure.indeed.com — sign in and Continue), then a new chat. Point to
/career-navigator:launchStep 3 for the full walkthrough. -
Assisted manual: Skip
search_jobs/get_job_details. After loading parameters from §1, provide 2-3 targeted query/link packs for each channel requested:- state/federal boards (e.g., IllinoisJobLink, USAJobs),
- niche boards (e.g., Wellfound, Welcome to the Jungle),
- company-direct/ATS pages (company careers, Greenhouse/Lever/Workday).
Ask the user to paste listings using the normalized schema from Source model and normalization. Pass what they provide to
job-scoutfor ranking; present with the §5 layout where links exist. Footer: note listings were user-provided (not live MCP) until connectors are connected.
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.
- 12d ago First seen · 231 lines · 41 tokens per session scan A 48d05964a743
search-jobs is a skill published in the GitHub repository tmargolis/career-navigator (13 stars, last pushed 13d ago), licensed Apache-2.0. It adds 41 tokens to every session and 2,830 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…