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 quote-to-cashgit 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/quote-to-cash)<a href="https://agentmods.dev/skills/hubspot/agent-cli-skills/quote-to-cash"><img src="https://agentmods.dev/badge/skills/hubspot/agent-cli-skills/quote-to-cash/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/quote-to-cash"><img src="https://agentmods.dev/badge/skills/hubspot/agent-cli-skills/quote-to-cash.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00029 | $0.01711 |
| Opus 5.5 | $0.00012 | $0.00684 |
| Sonnet 5.5 | $0.00006 | $0.00342 |
| Haiku 4.5 | $0.00003 | $0.00171 |
Grade A, and why
quote-to-cash 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 1mo 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resources
| File | When to use |
|---|---|
resources/q2c-essentials.md |
Six-field cheat sheet, association directions, portal caveats for invoices/subscriptions/orders/carts. |
Foundations
Read bulk-operations/SKILL.md first — JSONL piping, batch read, pagination, and the dry-run/digest/confirm flow for destructive ops live there. Reshape recipes (read → write payload) are in bulk-operations/resources/json-patterns.md.
hubspot <command> --help is the source of truth. Object types are plural (products, line_items, quotes, invoices, subscriptions). Never hardcode property tables — hubspot properties list --type <type> is one call away. Verify any enum value the agent is about to write with hubspot properties options-list --type <type> <property> | jq -r '.value'.
Portal note: invoices, subscriptions, orders, carts show an empty objectTypeId in hubspot objects types. They work through objects search/list when the token has the matching scope (invoices-read, subscriptions-read, etc.) and 403 otherwise. CLI-created quotes are always DRAFT; approval routing, share links, PDF generation, and invoice creation usually require the HubSpot UI.
1. Create a product
hubspot objects create --type products \
--property name="Enterprise License" \
--property price=12000 \
--property hs_sku=ENT-001
For a recurring product set recurringbillingfrequency; check the API enum values first with hubspot properties options-list --type products recurringbillingfrequency | jq -r '.value'. Bulk-import a catalog by piping JSONL of {"properties":{...}} to hubspot objects create --type products --dry-run.
2. Build a quote: line items → quote → associations
objects create emits one result line per stdin line, in input order. That lets you build line items, capture their IDs, and associate them to the new quote in three pipes — no per-record shell loop.
DEAL_ID=12345
# 1. Create the line items. items.jsonl holds {"name":..,"qty":..,"price":..,"product_id":..} per line.
jq -c '{properties:{
name:.name, quantity:(.qty|tostring), price:(.price|tostring),
hs_product_id:.product_id, hs_line_item_currency_code:"USD"
}}' items.jsonl \
| hubspot objects create --type line_items > /tmp/lineitems.jsonl
# 2. Create the quote.
QUOTE_ID=$(hubspot objects create --type quotes \
--property hs_title="Acme Corp - 2026" \
--property hs_expiration_date=2026-06-30 \
--property hs_currency=USD \
--format json | jq -r '.data.id // .id')
# 3. Associate every new line item to the quote in one pipe.
jq -r '.id' /tmp/lineitems.jsonl \
| jq -cR --arg q "$QUOTE_ID" '{from:("quotes:" + $q), to:("line_items:" + .)}' \
| hubspot associations create
# 4. Link the quote to the deal.
hubspot associations create --from "deals:$DEAL_ID" --to "quotes:$QUOTE_ID"
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.
- 1mo ago Changed d509ce2fdb50
- 1mo ago Changed 1342100d7ac9
- 1mo ago Changed b331b16b8563
- 2mo ago First seen · 130 lines · 29 tokens per session scan A 96d3ead568ea
quote-to-cash is a skill published in the GitHub repository HubSpot/agent-cli-skills (28 stars, last pushed 9d ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,711 once invoked, about $0.0001 per session on Opus 5.5. 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.
quote-to-cash compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| quote-to-cashHubSpot/agent-cli-skills | Skill | 28 | 9d ago | Apache-2.0 | A | 29 | Claude Code, Codex |
| asc-ppp-pricingrorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 45 | Claude Code |
| snaplii-cliSnaplii-Inc/agent-to-merchant-payments | Skill | 812 | 2d ago | Apache-2.0 | A | 184 | Claude Code |
| stripeCraftOS-dev/CraftBot | Skill | 402 | 2d ago | MIT | A | 79 | Claude Code, Codex |
| ai-slopwaybarrios/opencode-power-pack | Skill | 551 | 5d ago | MIT | A | 61 | Claude Code |
| stripemagnus919/agent-skills | Skill | 166 | 2d ago | MIT | A | 116 | Claude Code, Codex |
| asc-ppp-pricinghanamizuki/solopreneur | Skill | 156 | 3d ago | MIT | A | 45 | Claude Code |