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 AdanRott/magnificent-jobs-plugin --skill skillgit clone --depth 1 https://github.com/AdanRott/magnificent-jobs-pluginWrote 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/adanrott/magnificent-jobs-plugin/skill)<a href="https://agentmods.dev/skills/adanrott/magnificent-jobs-plugin/skill"><img src="https://agentmods.dev/badge/skills/adanrott/magnificent-jobs-plugin/skill/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/adanrott/magnificent-jobs-plugin/skill"><img src="https://agentmods.dev/badge/skills/adanrott/magnificent-jobs-plugin/skill.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 | $0.00083 | $0.01513 |
| Opus 5 | $0.00042 | $0.00757 |
| Sonnet 5 | $0.00017 | $0.00303 |
| Haiku 4.5 | $0.00008 | $0.00151 |
Grade A, and why
find-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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- find-jobs — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find jobs with Magnificent Jobs
You have live access to 3.5M+ US job postings pulled hourly from company applicant-tracking systems. Search is by meaning: pass what the person wants in plain English, not boolean keywords. Never invent jobs — only report what the tools return. The goal is not "a list" — it is that this person actually finds a job they can get.
The flow: 1) who they are → 2) what they want → 3) search
Keep it conversational — two short questions, then search. Never block: if they skip a step, go with what you have.
1. Collect the resume — or a job title. If you don't already know their background, ask: "Paste your resume/CV (or point me to the file) — or just tell me the job title you're after." Read a resume fully; note titles, years, skills, industries, and secondary experience.
2. Ask what they actually want. One compact question covering: what kind of work they enjoy / want more of (and anything they want to avoid), where (city + radius, state, or remote), and hard constraints (seniority, salary floor, full-time/contract, visa). Example: "What do you want next — more of the same, a step up, or a shift toward something you enjoy more? And where: a city, a state, or remote?" If the resume and the answer disagree (e.g. resume says backend, they want ML), the answer wins and the resume supplies the angles.
3. Search — from several angles (below), merge, present, then iterate with them.
A person is more than one job title — always search from several angles
Never run a single query. Build 3–6 distinct queries and run them all (parallel calls are
fine), then merge, dedupe by url, and present the best across all of them. Angles:
- The obvious title they asked for ("Machine Learning Engineer …").
- Adjacent titles for the same work — different companies name the same role differently ("AI Engineer", "Applied Scientist", "MLOps Engineer", "Data Scientist, ML").
- Skill-led — their strongest tools/stack as the centre of the query ("Python PyTorch model deployment engineer").
- Domain-led — their industry experience ("machine learning engineer healthcare / fintech / robotics"), because domain-matched postings convert better.
- Seniority up and down one step when it is borderline (senior ↔ staff, mid ↔ senior).
- Secondary experience from the resume — if they also did backend, data engineering, product, teaching, ops, etc., run one query for that too and tell them you did ("you also have 3 years of data-engineering work, so I included those — 2 strong matches").
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 · 92 lines · 83 tokens per session scan A 465c33f7e8ae
find-jobs is a skill published in the GitHub repository AdanRott/magnificent-jobs-plugin (2 stars, last pushed 20d ago), licensed MIT. It adds 83 tokens to every session and 1,513 once invoked, about $0.0004 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
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…