Borrowing it
Nothing to install: this file belongs to ananta888/job-search-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ananta888/job-search-mcp/main/.opencode/skills/job-crawler/SKILL.mdgit clone --depth 1 https://github.com/ananta888/job-search-mcpWrote 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/ananta888/job-search-mcp/job-crawler)<a href="https://agentmods.dev/skills/ananta888/job-search-mcp/job-crawler"><img src="https://agentmods.dev/badge/skills/ananta888/job-search-mcp/job-crawler/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/ananta888/job-search-mcp/job-crawler"><img src="https://agentmods.dev/badge/skills/ananta888/job-search-mcp/job-crawler.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 | $0.00099 | $0.01559 |
| Opus 5 | $0.00049 | $0.00779 |
| Sonnet 5 | $0.00020 | $0.00312 |
| Haiku 4.5 | $0.00010 | $0.00156 |
Grade A, and why
job-crawler 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
job-crawler
Workflow für die Analyse von Job- und Vermittlungsportalen mit dem lokalen Webcrawler des Unterrichtslabors. Die Lernkette des Projekts lautet:
UI → Capture → Normalisierung → Policy → Replay → Validierung → Matching
Für lokale JSON-Portale sind Discovery und Capture im job-crawler-MCP-Server
zusammengefasst; die Sicherheitsstufen (Policy, Validierung) laufen trotzdem
immer mit.
Schritt 1 – Profil laden
Lies das Jobprofil mit dem MCP-Tool lade_profil. Standarddatei:
job-profile.json. Das Profil wird gegen
schemas/job-profil.schema.json validiert. Felder: suchbegriffe,
skills_pflicht, skills_wunsch, orte, arbeitsmodelle, gehalt_min,
gehalt_max, sprachen, min_erfahrung_jahre.
Schritt 2 – Portale und Browser prüfen
Rufe liste_portale auf. Beachte neben erlaubt auch status und
zugangsart: Nur aktive Adapter dürfen automatisiert laufen. Lokale Portale
(kind: local) sind standardmäßig erlaubt; echte Portale benötigen
enabled: true, ALLOW_EXTERNAL_PORTALS=1 und die explizite Nutzerfreigabe.
Rufe browser_status nur für Browserportale auf. Öffentliche APIs und RSS-Feeds
benötigen weder Browser noch Sitzung.
Schritt 3 – Angebote sammeln
Rufe suche_angebote auf. Der Server crawlt alle erlaubten lokalen Portale
gegen die jeweilige Policy-Allowlist und validiert jede Antwort gegen das
Portal-Schema (schemas/job-portal-response.schema.json). Ergebnisse werden
bereits per suchbegriffe des Profils gefiltert.
Für echte Quellen rufe bevorzugt mehrportal_suche(query=..., ort=...) auf.
Ohne portal_ids fragt sie StepStone, Arbeitnow, Remotive und We Work Remotely
ab; ein Quellenausfall blockiert die übrigen Resultate nicht. Nutze
portal_suche(portal_id=...) für eine gezielte Einzelabfrage. Arbeitnow,
Remotive und We Work Remotely laufen über offiziell angebotene APIs/Feeds.
Erhalte bei Remotive und We Work Remotely immer Portalname und Original-Link.
Schritt 4 – Bewerten
Rufe bewerte_angebote mit den gesammelten Angeboten auf. Die Bewertung ist
deterministisch:
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 · 124 lines · 99 tokens per session scan A b8673b1d717c
job-crawler is a skill published in the GitHub repository ananta888/job-search-mcp (0 stars, last pushed 18d ago), licensed BSD-3-Clause. It adds 99 tokens to every session and 1,559 once invoked, about $0.0005 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…