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 huskar20/huskar20-plugins --skill setupgit clone --depth 1 https://github.com/huskar20/huskar20-pluginsWrote 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/huskar20/huskar20-plugins/setup)<a href="https://agentmods.dev/skills/huskar20/huskar20-plugins/setup"><img src="https://agentmods.dev/badge/skills/huskar20/huskar20-plugins/setup/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/huskar20/huskar20-plugins/setup"><img src="https://agentmods.dev/badge/skills/huskar20/huskar20-plugins/setup.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 | $0.00096 | $0.03368 |
| Opus 5.5 | $0.00038 | $0.01347 |
| Sonnet 5.5 | $0.00019 | $0.00674 |
| Haiku 4.5 | $0.00010 | $0.00337 |
Grade A, and why
setup 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 1mo 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Career Hunter — Setup
Onboard a new user end to end: interview → profile file → tracker spreadsheet →
automation config. Everything the apply and sync skills need is produced here.
Re-running setup is safe: offer to update the existing profile instead of starting over.
Outputs (all in the user's working folder)
| File | Purpose |
|---|---|
career-profile.md |
Canonical answers for every application form. The user edits it by hand afterward; other skills re-read it every run. |
career-hunter-state/config.json |
Spreadsheet ID, resume path, submission mode, caps, schedule, notification prefs. |
career-hunter-state/seen_jobs.json |
Created empty; the apply skill's dedupe memory. |
career-hunter-state/last_run.json |
Created with null fields; the sync skill's watermark. |
Step 1 — Check prerequisites
Verify each connector is actually present (list the available tools / connectors, don't assume), and tell the user plainly what is missing rather than failing later. A plugin cannot gate its own installation on connectors — this check is the real gate, so do it thoroughly and stop if a required piece is absent.
- Gmail connector — needed by sync (and apply, for email verification codes).
- Google Drive connector — creates the tracker spreadsheet by copying the
published template (
copy_file) and reads it for dedupe in apply/sync. - Google Calendar connector — needed so sync can create an event when it detects a confirmed interview. If it's missing, say so; the user can still proceed (sync will fall back to notification-only) but flag it as a TODO.
- Claude-in-Chrome extension, connected —
list_connected_browsers; writes application rows and fills application forms, in the user's own Chrome session. Setup itself no longer needs it for the tracker (the template copy brings the structure with it), but apply and sync do — there is no Sheets-cell MCP, so every cell write goes through Chrome. If it's missing, setup can still finish; flag it as a TODO. - Resume file — ask the user to place their resume PDF in the working folder (or a subfolder) and confirm its path. Record it in config. If they don't have it ready, continue setup and leave a TODO in the summary.
What ships with it
2 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.
- 1mo ago First seen · 242 lines · 96 tokens per session scan A fc508f0c519e
setup is a skill published in the GitHub repository huskar20/huskar20-plugins (5 stars, last pushed 10d ago), licensed MIT. It adds 96 tokens to every session and 3,368 once invoked, about $0.0004 per session on Opus 5.5. 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…