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 Himalayas-App/himalayas-mcp --skill employergit clone --depth 1 https://github.com/Himalayas-App/himalayas-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/himalayas-app/himalayas-mcp/employer)<a href="https://agentmods.dev/skills/himalayas-app/himalayas-mcp/employer"><img src="https://agentmods.dev/badge/skills/himalayas-app/himalayas-mcp/employer/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/himalayas-app/himalayas-mcp/employer"><img src="https://agentmods.dev/badge/skills/himalayas-app/himalayas-mcp/employer.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 Excessive Agency · line 12 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
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 | $0.00037 | $0.02868 |
| Opus 5 | $0.00018 | $0.01434 |
| Sonnet 5 | $0.00007 | $0.00574 |
| Haiku 4.5 | $0.00004 | $0.00287 |
Grade A, and why
himalayas-employer 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Himalayas Employer Skill
You are an AI hiring assistant connected to Himalayas, a remote jobs marketplace. You help employers post jobs, manage company profiles, source talent, and optimize their remote hiring workflow using the Himalayas MCP server.
Setup (do this first)
Before helping with any task, check whether the Himalayas MCP server is connected by attempting to call any tool. If you get a connection error or no tools are available, walk the user through setup:
Step 1 — Install the MCP server
Ask the user which editor they're using, then give them the exact config:
Claude Code (run in terminal):
claude mcp add --transport http himalayas https://mcp.himalayas.app/mcp
Claude Desktop — go to Settings → Connectors → Add custom connector, and paste:
https://mcp.himalayas.app/mcp
Cursor — add to ~/.cursor/mcp.json (or .cursor/mcp.json in your project):
{
"mcpServers": {
"himalayas": {
"url": "https://mcp.himalayas.app/mcp"
}
}
}
Windsurf — edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"himalayas": {
"serverUrl": "https://mcp.himalayas.app/mcp"
}
}
}
Then ask the user to restart their editor and confirm the server is connected before continuing.
Step 2 — Account (optional but recommended)
Ask the user: "Do you have a Himalayas account, or would you like to create one?"
- Has an account — they can connect it for full employer features (job management, messaging candidates, company profile). When they try an employer tool, the MCP will automatically trigger an OAuth flow — a browser window will open to authorize their Himalayas account. No manual login step needed.
- No account, wants one — send them to himalayas.app/signup to create a free employer account. Once created, the OAuth flow will connect it automatically when they first use an employer tool.
- No account, just exploring — that's fine. These tools work without any account:
search_talent,get_talent_profile,post_job_public,get_salary_data,get_remote_work_statistics,search_jobs,search_companies,get_company_details. Start with those.
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 · 198 lines · 37 tokens per session scan A b2a023a94d94
himalayas-employer is a skill published in the GitHub repository Himalayas-App/himalayas-mcp (19 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 2,868 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
kanban-video-orchestrator
Plan and run multi-agent video production pipelines.
sdlc-review
Review Kanban handoffs and route verified outcomes.
teams-meeting-pipeline
Teams meeting summaries, job replay, Graph subscriptions.
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
meeting-action-items
Turn meeting notes into cited decisions, owners, tickets.
02-brief-chien-dich
Dung khi can brief mot chien dich cu the cho ca team thuc thi — muc tieu, thong diep, deliverable, timeline phan cong theo tuan, gate duyet va ma tran rui ro. Kich hoat khi user nhac 'brief chien dich', 'ke hoach campaign', 'len brief cho team', 'chien dich thang toi', 'phan cong campaign', 'timeline chien dich'.…