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 ankurmans/whooshly-mcp --skill whooshly-setupgit clone --depth 1 https://github.com/ankurmans/whooshly-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/ankurmans/whooshly-mcp/whooshly-setup)<a href="https://agentmods.dev/skills/ankurmans/whooshly-mcp/whooshly-setup"><img src="https://agentmods.dev/badge/skills/ankurmans/whooshly-mcp/whooshly-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/ankurmans/whooshly-mcp/whooshly-setup"><img src="https://agentmods.dev/badge/skills/ankurmans/whooshly-mcp/whooshly-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 | $0.00059 | $0.00792 |
| Opus 5.5 | $0.00024 | $0.00317 |
| Sonnet 5.5 | $0.00012 | $0.00158 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
whooshly-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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Whooshly
Whooshly is a link, QR, and campaign toolkit. This plugin bundles a remote MCP
connection to https://app.whooshly.co/api/mcp, so its tools are available
directly once the user has connected an account — no local server to run.
Connecting an account
Every tool acts on the user's own Whooshly account and requires the one-time
Core plan (or Pro) to be unlocked; get_billing_status works on any
account so it can be checked before anything else.
- Claude.ai / Desktop / mobile: the remote server prompts an OAuth consent screen the first time a tool is called. No manual setup needed.
- Claude Code / header-based clients: the user mints a token at
https://app.whooshly.co/agentsand adds it as a bearer header, e.g.claude mcp add --transport http whooshly https://app.whooshly.co/api/mcp --header "Authorization: Bearer <token>".
If a tool call fails with core_locked or pro_required, tell the user what
plan is needed and point them at https://app.whooshly.co to upgrade — do not
guess at a workaround.
What each tool does
get_billing_status— check plan/entitlement before doing anything else.create_link/update_link/list_links/get_link_stats— short links with custom slugs and exact click totals.create_qr/get_qr— a dynamic QR code (a short link whose QR is returned as a scannable PNG image, not just a URL). Because it's dynamic, the destination can change later without reprinting anything.create_utm/list_utm— reusable UTM parameter templates.create_vcard— a hosted digital business card page.create_page/update_page/list_pages/get_page— hosted landing pages built from content blocks, with lead-capture forms. Creating a page requires the account's subdomain to already be claimed once in the app (under Funnels) — if a call fails withno_subdomain, tell the user to do that first, then retry.search/fetch— search the account's existing links and pages, then fetch one by id.
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 · 65 lines · 59 tokens per session scan A 7f00893d04bf
whooshly-setup is a skill published in the GitHub repository ankurmans/whooshly-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 792 once invoked, about $0.0002 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 2026-09-21.
whooshly-setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| whooshly-setupankurmans/whooshly-mcp | Skill | 0 | yesterday | MIT | A | 59 | Claude Code |
| qrvelozneaj-Corp/qrverloz-mcp | Skill | 3 | 6mo ago | MIT | A | 25 | Claude Code, Codex |
| threebrowser-studio-mcpSamG-Coder/ThreeBrowserStudio | Skill | 25 | 4d ago | MIT | A | 122 | Codex |
| onplana-project-plannerOnplana/onplana-mcp-server | Skill | 5 | 18d ago | MIT | A | 133 | Claude Code |
| just-publishjust-done/just-publish-mcp | Skill | 1 | yesterday | MIT | A | 195 | Codex |
| onplana-autonomous-agentOnplana/onplana-mcp-server | Skill | 5 | 18d ago | MIT | A | 102 | Claude Code |
| mcp-ads-professional-campaignerRoyAzran/mcp-ads | Skill | 3 | 5d ago | MIT | A | 55 | Claude Code, Codex |