hubspot-social-task-runner

hubspot-social-task-runner is a skill for Claude Code from First-Touch-Inc/firsttouch-agent-skill-packs. It costs 83 tokens per session (2,119 once invoked), scanned A, original, MIT.

A workflow that finds LinkedIn and other social-action tasks due today in HubSpot, a customer-relationship management system, then carries out approved actions and completes the matching tasks.

In plain words
What is it for?
It helps run due LinkedIn connection, message, and follow-up tasks through FirstTouch, then close each HubSpot task after the action is queued or sent.
Why use it?
It turns an existing daily task queue into completed social work while keeping the CRM task status accurate. It does not create new task schedules or fill in missing setup.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ae-pack plugin — 13 skills, 1 MCP server shipped together

Good fit It helps run due LinkedIn connection, message, and follow-up tasks through FirstTouch, then close each HubSpot task after the action is queued or sent.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/first-touch-inc/firsttouch-agent-skill-packs/hubspot-social-task-runner
Install

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.

Any agent
npx skills add First-Touch-Inc/firsttouch-agent-skill-packs --skill hubspot-social-task-runner
Clone the repo
git clone --depth 1 https://github.com/First-Touch-Inc/firsttouch-agent-skill-packs

Made for: Claude Code.

Or install ae-pack, the plugin that ships this one along with the rest of its 13 skills, 1 MCP server.

Wrote 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.

agentmods badge for hubspot-social-task-runner

README.md
[![agentmods](https://agentmods.dev/badge/skills/first-touch-inc/firsttouch-agent-skill-packs/hubspot-social-task-runner/github.svg)](https://agentmods.dev/skills/first-touch-inc/firsttouch-agent-skill-packs/hubspot-social-task-runner)
Your own site
<a href="https://agentmods.dev/skills/first-touch-inc/firsttouch-agent-skill-packs/hubspot-social-task-runner"><img src="https://agentmods.dev/badge/skills/first-touch-inc/firsttouch-agent-skill-packs/hubspot-social-task-runner/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.

agentmods 80×15 button for hubspot-social-task-runner

Your own site · 80×15
<a href="https://agentmods.dev/skills/first-touch-inc/firsttouch-agent-skill-packs/hubspot-social-task-runner"><img src="https://agentmods.dev/badge/skills/first-touch-inc/firsttouch-agent-skill-packs/hubspot-social-task-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,119 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00083 $0.02119
Opus 5 $0.00042 $0.01059
Sonnet 5 $0.00017 $0.00424
Haiku 4.5 $0.00008 $0.00212

Measured 12d ago against content hash f12550760d2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

hubspot-social-task-runner 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.

plugins/ae-pack/skills/hubspot-social-task-runner/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HubSpot Social Task Runner

Outcome: Turn an existing HubSpot task queue into completed LinkedIn/social actions for the tasks due today. This play does not create a new cadence, infer missing task logic, or replace RevOps setup. It only works when HubSpot already has daily social-step tasks such as LinkedIn connect, LinkedIn message, or social follow-up.

First-run onboarding gate

Before running this skill for the first time in a workspace, load ../../references/onboarding.md and complete the onboarding questions. Do not proceed until you know: LinkedIn account type, HubSpot MCP status, FirstTouch sender/account readiness, and whether HubSpot tasks are already being created daily for social steps. If HubSpot MCP cannot read and complete tasks, or if no task queue exists, stop and recommend setting up the task source first.

Example prompts

  • "Find my HubSpot LinkedIn tasks due today and execute the eligible ones through FirstTouch."
  • "Work the LinkedIn connection request and LinkedIn message tasks due today in my HubSpot queue."
  • "Check my HubSpot tasks for LinkedIn/social follow-ups due today, run the safe ones, and tell me what stayed open."

When to use

  • "Work my HubSpot LinkedIn tasks due today"
  • "Automate the manual social tasks my team already creates"
  • "Find all due HubSpot tasks that say connect on LinkedIn or send LinkedIn message, then run them"
  • AE/BDR teams that already get daily CRM tasks for social touches but waste time manually clicking through them

When NOT to use

  • There are no HubSpot/CRM tasks already being created for social steps
  • The CRM connector is not connected or cannot expose tasks
  • The user wants a new cadence/list/flow created. Use hubspot-signal-to-linkedin-touch, social-campaigns, or icp-outbound-builder instead.
  • The task is ambiguous, missing a contact, missing a LinkedIn URL, missing sender/owner, or not clearly a LinkedIn/social action
  • The task is an email/call/manual research task rather than a LinkedIn connect/message/social follow-up

Read the full file on GitHub · 152 lines

Changes

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.

  1. 12d ago First seen · 152 lines · 83 tokens per session scan A f12550760d2d

Subscribe to this mod's changes

hubspot-social-task-runner is a skill published in the GitHub repository First-Touch-Inc/firsttouch-agent-skill-packs (5 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 2,119 once invoked, about $0.0004 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 2026-08-31.