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 iblai/enterprise-agents --skill hubspotgit clone --depth 1 https://github.com/iblai/enterprise-agentsWrote 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/iblai/enterprise-agents/hubspot)<a href="https://agentmods.dev/skills/iblai/enterprise-agents/hubspot"><img src="https://agentmods.dev/badge/skills/iblai/enterprise-agents/hubspot/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/iblai/enterprise-agents/hubspot"><img src="https://agentmods.dev/badge/skills/iblai/enterprise-agents/hubspot.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 | $0.00037 | $0.00519 |
| Opus 5 | $0.00018 | $0.00260 |
| Sonnet 5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
hubspot 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 10d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HubSpot
What it is
HubSpot is a widely adopted CRM and inbound marketing platform used by enterprise sales, marketing, and customer success teams. In this segment the sales enablement and marketing agents use HubSpot to retrieve deal stage and pipeline context, look up contact and company records, review campaign performance metrics, and check marketing workflow enrollment status. It complements Salesforce in organizations that use both platforms.
When to use this skill
- Looking up a deal's current stage, associated contacts, and close date for deal prep
- Searching for a company or contact record to understand the engagement history
- Retrieving marketing campaign performance (sessions, contacts generated, influenced revenue)
- Checking workflow enrollment status or step completion for a marketing sequence
- Reading email asset open and click rates to assess campaign effectiveness
Credentials
This skill authenticates using variables from ~/.openclaw/.env (template: .env.example at the config root). Required variables:
HUBSPOT_ACCESS_TOKEN- private app access token (preferred over legacy API keys)
Key operations
GET /crm/v3/objects/deals/{dealId}- retrieve a deal recordGET /crm/v3/objects/contacts/search- search contacts by email or propertyGET /crm/v3/objects/companies/{companyId}- retrieve a company recordGET /marketing/v3/campaigns- list marketing campaignsGET /automation/v4/flows/{workflowId}- retrieve workflow definition and enrollment countsPOST /crm/v3/objects/notes- log a note against a CRM record
Notes
- Use private app access tokens; legacy API keys were deprecated in November 2022.
- Rate limit: 110 requests/10 seconds and 150,000/day for free/starter; higher tiers have higher limits.
- CRM search endpoint supports filtering, sorting, and property selection to minimize response payload.
- HubSpot has a sandbox portal (developer test account) separate from production; use for non-production testing.
- Association APIs are needed to traverse relationships between deals, contacts, and companies.
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.
- 10d ago First seen · 37 lines · 37 tokens per session scan A db890088dd09
hubspot is a skill published in the GitHub repository iblai/enterprise-agents (11 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 519 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
availity
Availity Essentials — lets an agent perform real-time eligibility verification, prior authorization initiation and status checks, and payer enrollment management via the Availity clearinghouse REST API.
cerner-fhir
Cerner Millennium FHIR R4 API — lets an agent read patient clinical data (demographics, encounters, diagnoses, medications, notes) within a Cerner-hosted health system.
epic-fhir
Epic EHR FHIR R4 API — lets an agent read and write patient clinical data (demographics, encounters, diagnoses, medications, notes, orders) within an Epic-hosted health system.
healthstream
HealthStream LMS — lets an agent query employee training transcripts, assign compliance curricula, check credential expiration alerts, and pull completion reports from the HealthStream learning management system.
innovaccer
Innovaccer — lets an agent query population health analytics, patient risk scores, care gap lists, and SDOH screening data from the Innovaccer unified patient data platform.
micromedex
Micromedex (Merative/IBM) — lets an agent perform drug interaction screening, dose range checking, toxicology lookups, and IV compatibility queries using the Micromedex drug knowledge base.