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 ishandutta2007/Awesome-AI-Job-Hunting --skill jobbank-searchgit clone --depth 1 https://github.com/ishandutta2007/Awesome-AI-Job-HuntingWrote 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/ishandutta2007/awesome-ai-job-hunting/jobbank-search)<a href="https://agentmods.dev/skills/ishandutta2007/awesome-ai-job-hunting/jobbank-search"><img src="https://agentmods.dev/badge/skills/ishandutta2007/awesome-ai-job-hunting/jobbank-search/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/ishandutta2007/awesome-ai-job-hunting/jobbank-search"><img src="https://agentmods.dev/badge/skills/ishandutta2007/awesome-ai-job-hunting/jobbank-search.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 | $0.00275 | $0.01882 |
| Opus 5 | $0.00138 | $0.00941 |
| Sonnet 5 | $0.00055 | $0.00376 |
| Haiku 4.5 | $0.00028 | $0.00188 |
Grade A, and why
jobbank-search 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.
This is a copy
100% identical to jobbank-search — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jobbank Search Skill
Search live Danish job listings from Akademikernes Jobbank — Denmark's primary job portal for highly educated candidates. Uses the RSS feed for search (up to 100 results) and JSON-LD parsing for detailed job information. Jobbank may block automated requests with Cloudflare bot protection; if that happens, report the portal as unavailable and use WebSearch fallback instead of retrying.
When to use this skill
Invoke this skill when the user wants to:
- Search for jobs, positions, or career opportunities in Denmark
- Find academic, graduate, trainee, Ph.d., or postdoc positions
- Look for jobs by keyword, industry, location, education background, or work function
- Find remote or hybrid positions in Denmark
- Get full details for a specific job posting on jobbank.dk
- Check what positions are available at a specific company on jobbank.dk
- Browse jobs suitable for new graduates or people with international backgrounds
Commands
Search jobs
bun run .agents/skills/jobbank-search/cli/src/cli.ts search [flags]
Key flags:
--key <text>— keyword search (title, company, keyword)--exclude <text>— exclude keywords from results--type <code>— job type:3=Fuldtidsjob,6=Graduate/trainee,13=Deltidsjob,8=Vikariat,12=Ph.d. & Postdoc,11=Freelance,9=Praktikplads,4=Studiejob (repeatable)--location <code>— region:2=Storkøbenhavn,8=Østjylland (Aarhus),7=Midtjylland,6=Nordjylland,13=Fyn (repeatable)--work-area <code>— function:31=IT-Software,43=Data & Analyse,26=Ledelse,29=Marketing (repeatable)--industry <code>— sector:10331=IT & Tele,10442=Forskning & Uddannelse,10358=Finans (repeatable)--education <code>— education field:24=IT,21=Økonomi & Revision,34=Samfundsvidenskab (repeatable)--remote <value>—helt(fully remote) ordelvist(partially remote)--suitable-for <code>—2=Nyuddannede,4=International baggrund,5=Erfarne--company <id>— filter by company ID--since <YYYY-MM-DD>— jobs posted on or after this date--limit <n>— cap results returned by CLI--format json|table|plain
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- cli/package.json 595 B
- cli/README.md 13 KB
- cli/src/cli.ts 1.6 KB runs code
- cli/src/commands/detail.ts 4.9 KB runs code
- cli/src/commands/search.ts 7.3 KB runs code
- cli/src/helpers.ts 6.6 KB runs code
- cli/tests/cli-contract.test.ts 910 B runs code
- cli/tests/cli-flag-validation.test.ts 3.6 KB runs code
- cli/tests/detail-jsonld.test.ts 1.3 KB runs code
- cli/tests/helpers.ts 959 B runs code
- cli/tests/request-timeout.test.ts 906 B runs code
- cli/tests/retry-backoff.test.ts 2.2 KB runs code
- cli/tests/rss-fetch.test.ts 599 B runs code
- cli/tests/rss-parsing.test.ts 3.2 KB runs code
- cli/tests/search-normalization.test.ts 1.4 KB runs code
- cli/tsconfig.json 489 B
- url-reference.md 10 KB
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 · 181 lines · 275 tokens per session scan A 4bb92343f558
jobbank-search is a skill published in the GitHub repository ishandutta2007/Awesome-AI-Job-Hunting (3 stars, last pushed 17d ago), licensed MIT. It adds 275 tokens to every session and 1,882 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to jobbank-search, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
thetoolforthat
Guide for discovering 540+ developer tools, design resources, AI platforms, and agencies using the thetoolforthat MCP server. Use when asked to find tools for a project, recommend tech stack components, discover design agencies, or search for specific tool categories.
ax-extract-workflow
Reconstructs the workflow behind a shipped artifact from ax session evidence, commits, and PR context. Use when asking what made a feature, fix, demo, or PR work, or when turning a past success into a repeatable recipe.
video-router
Guides agents to select and lock a video-production route. Use when a brief must be classified as generation, deterministic composition, footage editing, or an end-to-end combination before production, asset creation, editing, or rendering begins.
xquik-public-data
Guides agents through safe Xquik public X data workflows using documented API, MCP, monitor, and webhook surfaces. Use when a task needs X/Twitter tweet, user, trend, list, community, article, monitor, or webhook data through Xquik.
hermes-tweet
Guides agents through safe Hermes Tweet X/Twitter plugin setup, read workflows, and explicit action gating. Use when installing Hermes Tweet, checking its Hermes Agent integration, or choosing read versus action tools.
eval-driven-development
Building rigorous LLM evaluation pipelines. Use when developing AI features to ensure quality and prevent regressions across different model versions.