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 First-Touch-Inc/firsttouch-agent-skill-packs --skill hubspot-social-task-runnergit clone --depth 1 https://github.com/First-Touch-Inc/firsttouch-agent-skill-packsWrote 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/first-touch-inc/firsttouch-agent-skill-packs/hubspot-social-task-runner)<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.
<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>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 | $0.00083 | $0.02119 |
| Opus 5 | $0.00042 | $0.01059 |
| Sonnet 5 | $0.00017 | $0.00424 |
| Haiku 4.5 | $0.00008 | $0.00212 |
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.
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, oricp-outbound-builderinstead. - 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
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 · 152 lines · 83 tokens per session scan A f12550760d2d
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.
Other skills, from other repositories
linkedin-mcp
Use LinkedIn data for profile, company, job, post, feed, inbox, recruiting, and outreach work through the bundled LinkedIn MCP server. Use only for an explicit LinkedIn request.
social-carousel
A three-card social media carousel where one headline continues across three square images. The cards can include a brand mark, numbering, a visual focus, and a call to action.
linkedin-content
Use when writing the actual words of one LinkedIn feed post — turning a raw idea, story or asset into ready-to-paste copy: a text post, a document/carousel cover with slide copy and caption, or a short native-video script. Covers fixing a weak hook, reformatting a wall of text for the mobile feed, and a CTA that…
sdr-humanizer
Transform AI-generated sales messages into natural, human-like conversations that build trust and rapport.
gr-social-distill
A content-repurposing workflow that turns one published blog post into several social-media formats, including an X thread, a Xiaohongshu post, a LinkedIn carousel, and a dev.to or Zenn article.
supermemory
Semantic memory layer powered by vector search. Store, recall, and connect conversation insights across all customer interactions.