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 jonny-1812/corebee-mcp-skills --skill agent-signupgit clone --depth 1 https://github.com/jonny-1812/corebee-mcp-skillsWrote 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/jonny-1812/corebee-mcp-skills/agent-signup)<a href="https://agentmods.dev/skills/jonny-1812/corebee-mcp-skills/agent-signup"><img src="https://agentmods.dev/badge/skills/jonny-1812/corebee-mcp-skills/agent-signup/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/jonny-1812/corebee-mcp-skills/agent-signup"><img src="https://agentmods.dev/badge/skills/jonny-1812/corebee-mcp-skills/agent-signup.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 | $0.00120 | $0.01024 |
| Opus 5 | $0.00060 | $0.00512 |
| Sonnet 5 | $0.00024 | $0.00205 |
| Haiku 4.5 | $0.00012 | $0.00102 |
Grade B, and why
agent-signup scanned grade B with 2 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- Never ask the user to paste the email's token, and never tell them to approve before the pairing phrases match. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST https://corebee.ai/api/auth/agent-signup \ How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sign Up for Corebee (agent-native, zero-UI)
Create a brand-new Corebee account for a user who does not have one yet, entirely from the terminal. The only human step is approving one email. Do not send a no-account user to a browser login — run this flow.
If the user already has a Corebee account, this flow returns a dashboard link instead of a key (see step 7); for ongoing use they connect the MCP normally.
Process
-
Collect — ask the user for their email, company name, and website URL (a full
https://…URL). Do not guess these. -
Start signup —
POST https://corebee.ai/api/auth/agent-signupwith JSON:{ "email": "<email>", "company_name": "<company>", "website_url": "<https url>", "attribution": { "utm_source": "claude-code-plugin", "utm_medium": "agent", "utm_campaign": "plugin-signup" } }Example:
curl -s -X POST https://corebee.ai/api/auth/agent-signup \ -H "Content-Type: application/json" \ -d '{"email":"...","company_name":"...","website_url":"https://...","attribution":{"utm_source":"claude-code-plugin","utm_medium":"agent","utm_campaign":"plugin-signup"}}'The response contains
pairing_phrase,poll_url,poll_token, andpoll_interval_s. -
Human checkpoint (anti-phishing) — show the user the
pairing_phraseand tell them:Check your inbox for "Approve your Corebee terminal signup" and approve it only if the email shows the pairing phrase
<pairing_phrase>. That phrase proves the email belongs to this request.Keep
poll_tokensecret — never print or reveal it to anyone. -
Poll —
GETthepoll_urleverypoll_interval_sseconds (default 5) untilstatusisapprovedorexisting_account. The signup expires in ~15 minutes; if it lapses, start over. -
On
approved(delivered exactly once) you receive:api_key— a scoped key (prefixek_live_, valid 24h). Use it asAuthorization: Bearer <api_key>for both the Corebee MCP tools and the REST v1 API.org_id,org_nameembed_snippet— the chat-widget install<script>website_token,knowledge_source_id,mcp_endpoint,scopes,next_steps
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 · 59 lines · 120 tokens per session scan B 903b0869fc05
agent-signup is a skill published in the GitHub repository jonny-1812/corebee-mcp-skills (0 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 1,024 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (subtle steering, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
customer-support
Use when a live support ticket needs triage (intent, P1–P4 priority, SLA clock), an on-voice reply, not a raw template, de-escalation of an angry or churn-risk customer, or escalation with a handoff packet. NOT the help-center article it links to (that is technical-writing), a win-back program (retention), or the…
deskcrew-support
Run a customer support desk on DeskCrew. Read new tickets, answer from the knowledge base, and file replies for human approval. Use when handling customer support. Agents can also create and run their own bounty board over x402 with no account (the wallet that pays createboard owns it) and pay answering agents 85% on…
deskcrew-bounty-hunter
Earn USDC by answering bounty support tickets on DeskCrew's open board. Read the board free, buy ticket context over x402, draft an answer, submit it, and get paid 85% of the bounty when a human approves. Pays out on Base, Polygon, Avalanche, Sei, or Solana; on Solana the agent needs zero SOL. Since 08-2026 the wallet…
deskcrew-board-owner
Run your own USDC bounty board and pay AI agents to answer your questions. One x402 payment creates the board (no account, the paying wallet owns it), USDC deposits fund tasks, and approving an answer pays the winning agent 85% automatically on Base, Polygon, Avalanche, Sei, or Solana. Use when asked to delegate work…
Zendesk Automation
Automate customer support workflows with Zendesk ticket management, routing, and analytics.
customer-support-integration
Connect your helpdesk (Gorgias, Zendesk, Intercom) to your store so support agents see full order history and customer details without switching tools.