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 Stupidoodle/swissdevjobs-cli --skill swissdevjobsgit clone --depth 1 https://github.com/Stupidoodle/swissdevjobs-cliWrote 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/stupidoodle/swissdevjobs-cli/swissdevjobs)<a href="https://agentmods.dev/skills/stupidoodle/swissdevjobs-cli/swissdevjobs"><img src="https://agentmods.dev/badge/skills/stupidoodle/swissdevjobs-cli/swissdevjobs/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/stupidoodle/swissdevjobs-cli/swissdevjobs"><img src="https://agentmods.dev/badge/skills/stupidoodle/swissdevjobs-cli/swissdevjobs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 50 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00109 | $0.01670 |
| Opus 5 | $0.00055 | $0.00835 |
| Sonnet 5 | $0.00022 | $0.00334 |
| Haiku 4.5 | $0.00011 | $0.00167 |
Grade A, and why
swissdevjobs 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 9d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jobs across 9 boards in 8 countries
The swissdevjobs MCP tools search multiple job boards. Call
list_boards first when board facts matter — per board it reports scope
(all-IT vs all-industries), currency, whether salary data is published,
whether it is search-driven, its category aliases, and whether it is
enabled. All enabled boards are searched by default; board on
search_jobs takes a board id (jobsch) or a country code (ch = every
Swiss board).
Search-driven boards (search_driven: true in list_boards): without
a query they only return their newest postings — always pass the user's
actual search terms for real coverage there, and pass a category alias to
keep all-industry boards on topic. The search result carries a note when
coverage was newest-only, and a boards_excluded map when a requested
filter (salary, remote, visa, level) does not exist on a board's wire —
those boards were not searched at all, not searched-and-empty; drop the
filter to include them. A tech filter still works on tagless boards: the
terms are matched server-side as full text (the note says so). contract
takes shared aliases (permanent, freelance, …) that every board maps
onto its own taxonomy; workload (percent) exists only on boards that
publish workload ranges — the rest are excluded visibly.
Summary rows omit empty fields entirely and carry
salary as numbers (salary_from/salary_to + currency); rows without
them come from boards that publish no salary data — that is the platform,
not a bug.
Tools
| tool | use it for |
|---|---|
list_boards |
board facts as data: scope, currency, salary, categories, apply capability |
search_jobs |
filter by salary, stack, city, board, remote, seniority, visa |
get_job |
the full posting before you write anything |
apply_to_job |
submit through the site's own form — gated, see below |
list_applications |
what has already been sent |
mark_applied |
record an application made by email or on an ATS |
top_technologies |
what the market is asking for right now |
What ships with it
8 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.
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.
- 9d ago First seen · 133 lines · 109 tokens per session scan A 3b54b3b964c3
swissdevjobs is a skill published in the GitHub repository Stupidoodle/swissdevjobs-cli (97 stars, last pushed 11d ago), licensed MIT. It adds 109 tokens to every session and 1,670 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 2026-08-30.
Other skills, from other repositories
ai-dev-jobs-mcp
Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP.
tensorpool-gpu-cloud
Safely inspect and operate TensorPool GPU clusters and jobs using the current tp CLI, with explicit approval before any billable or destructive action.
ai-dev-jobs-mcp-v2
AI Dev Jobs MCP workflow skill. Use this skill when the user needs Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP and the operator should preserve the upstream workflow, copied support files, and provenance before…
job-navigation-skill
Research current job markets and hiring requirements, analyze recent job descriptions, compare them with a user's resume, projects, skills, and constraints, and turn the gaps into prioritized career actions. Use for students, job seekers, and career changers who need industry or role trends, cross-platform JD…
worldjobplus-collect
A read-only collector for public overseas job postings from WorldJobPlus, a Korean government employment portal for jobs abroad. It returns the listings as normalized JSON, a consistent machine-readable format.
apple-jobs-collect
Collect recent public job postings from Apple's careers site (jobs.apple.com), default Korea, by keyword and location. Use when the user wants to gather, scan, or monitor Apple job listings for a role or region. Read-only — no login, save, or apply. Prints a normalized JSON array of postings.