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 agentmods add skills/hubspot/agent-cli-skills/audience-targetingnpx skills add HubSpot/agent-cli-skills --skill audience-targetinggit clone --depth 1 https://github.com/HubSpot/agent-cli-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/hubspot/agent-cli-skills/audience-targeting)<a href="https://agentmods.dev/skills/hubspot/agent-cli-skills/audience-targeting"><img src="https://agentmods.dev/badge/skills/hubspot/agent-cli-skills/audience-targeting.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.01461 |
| Opus 5 | $0.00019 | $0.00731 |
| Sonnet 5 | $0.00008 | $0.00292 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
audience-targeting 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 6d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foundation
Read bulk-operations/SKILL.md first — pagination, JSONL piping, destructive-op safety. Reshape recipes in bulk-operations/resources/json-patterns.md. Resource: resources/contact-segmentation-filters.md is the filter-expression cookbook (lifecycle, lead status, email engagement, activity, deals, owner).
Filter syntax cheat sheet
Source of truth: hubspot objects search --help.
- One
--filterflag = one AND group:--filter "lifecyclestage=lead AND !hubspot_owner_id". - Multiple
--filterflags are OR'd. Use for enum-OR-enum. - Operators:
=,!=,>,>=,<,<=,~(CONTAINS_TOKEN — whole-word, NOT substring). - HAS_PROPERTY: bare
nameorname?. NOT_HAS_PROPERTY:!name. Dates:YYYY-MM-DD.
~ gotcha: jobtitle~director matches the token "director", not arbitrary substrings. No regex operator — search broadly, post-filter with jq.
Properties this skill turns on
Full live list: hubspot properties list --type contacts. Enum options aren't exposed by properties get; discover with hubspot objects list --type contacts --properties <name> --limit 100 --format json | jq -r '.data[].properties.<name> // empty' | sort -u.
Core fields used here: lifecyclestage, hubspot_owner_id (bare/! for owned/unowned; hubspot owners list for IDs), hs_email_optout (!=true excludes opted-out), hs_email_last_open_date / notes_last_contacted (recency), jobtitle / country / city (string = or ~), num_associated_deals (0 net-new, >=1 has-pipeline).
Firmographics (industry, numberofemployees, annualrevenue) live on companies — see cross-object section.
Common segments
# Recent leads (this quarter, not yet owned)
hubspot objects search --type contacts \
--filter "lifecyclestage=lead AND createdate>2026-01-01 AND !hubspot_owner_id" \
--properties email,firstname,lastname,createdate
# Decision-makers by jobtitle (OR across tokens)
hubspot objects search --type contacts \
--filter "jobtitle~director" --filter "jobtitle~vp" --filter "jobtitle~chief" \
--properties email,jobtitle,company
# Engaged but not yet MQL (opened recently, still lead, opted in)
hubspot objects search --type contacts \
--filter "lifecyclestage=lead AND hs_email_last_open_date>2026-04-01 AND hs_email_optout!=true" \
--properties email,firstname,hs_email_last_open_date
# Geographic — US contacts opted in
hubspot objects search --type contacts \
--filter "country=United States AND hs_email_optout!=true" \
--properties email,state,city
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 118 lines · 39 tokens per session scan A 76e61e1b378a
audience-targeting is a skill published in the GitHub repository HubSpot/agent-cli-skills (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 1,461 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…