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 HubSpot/agent-cli-skills --skill deal-managementgit 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/deal-management)<a href="https://agentmods.dev/skills/hubspot/agent-cli-skills/deal-management"><img src="https://agentmods.dev/badge/skills/hubspot/agent-cli-skills/deal-management/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/hubspot/agent-cli-skills/deal-management"><img src="https://agentmods.dev/badge/skills/hubspot/agent-cli-skills/deal-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00038 | $0.02210 |
| Opus 5 | $0.00019 | $0.01105 |
| Sonnet 5 | $0.00008 | $0.00442 |
| Haiku 4.5 | $0.00004 | $0.00221 |
Grade A, and why
deal-management 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 9d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resources
| File | When to use |
|---|---|
resources/lifecycle-stage-progression.md |
Lifecycle stage API values + the contact-side updates that pair with deal moves. |
resources/stalled-deal-queries.md |
Filter cookbook for stalled / no-activity / past-close-date deals with dynamic dates. |
Foundations
Read bulk-operations/SKILL.md first — JSONL piping, batch read, pagination, and the dry-run/digest/confirm flow live there. Reshape recipes are in bulk-operations/resources/json-patterns.md. hubspot <command> --help is the source of truth. Object types are plural (contacts, deals, companies). For property reference: hubspot properties list --type deals — don't hardcode property tables.
1. Discover pipelines and stages
Pipeline and stage IDs are portal-specific. Always discover at runtime — never hardcode across portals.
hubspot pipelines list --type deals --format jsonl
# {"id":"default","label":"Sales Pipeline","displayOrder":0}
# {"id":"a1b2c3d4-0000-0000-0000-000000000000","label":"Enterprise Pipeline","displayOrder":1}
hubspot pipelines stages --type deals --pipeline default --format jsonl
# {"id":"appointmentscheduled","label":"Appointment Scheduled","displayOrder":0}
# {"id":"qualifiedtobuy","label":"Qualified To Buy","displayOrder":1}
# ...
# {"id":"closedwon","label":"Closed Won","displayOrder":5}
# {"id":"closedlost","label":"Closed Lost","displayOrder":6}
Grab a specific stage ID by label:
QUALIFIED=$(hubspot pipelines stages --type deals --pipeline default --format jsonl \
| jq -r 'select(.label=="Qualified To Buy") | .id')
The IDs shown above (appointmentscheduled, closedwon, etc.) are HubSpot's standard default deal pipeline stages — but discover yours every run since portals can rename or remove them.
2. Qualify an MQL into a deal
Find connected MQLs without a deal, then for each: create the deal, associate to contact + company, promote lifecycle.
# 1. find ready MQLs
hubspot objects search --type contacts \
--filter "lifecyclestage=marketingqualifiedlead AND hs_lead_status=CONNECTED AND num_associated_deals=0" \
--properties email,firstname,lastname,company,hubspot_owner_id
# 2. for one contact: company lookup, deal create, associate, promote
hubspot associations list --from contacts:<contact_id> --to companies # → <company_id>
hubspot objects create --type deals \
--property "dealname=Acme Corp - Inbound" \
--property pipeline=default --property dealstage=qualifiedtobuy \
--property amount=0 --property hubspot_owner_id=<owner_id>
# returns {"id":"<deal_id>","ok":true,...}
hubspot associations create --from deals:<deal_id> --to contacts:<contact_id>
hubspot associations create --from deals:<deal_id> --to companies:<company_id>
hubspot objects update --type contacts <contact_id> \
--property lifecyclestage=salesqualifiedlead --property hs_lead_status=OPEN_DEAL
What ships with it
2 files 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.
- 9d ago First seen · 181 lines · 38 tokens per session scan A de039e229944
deal-management is a skill published in the GitHub repository HubSpot/agent-cli-skills (23 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 2,210 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…