anthropics/claude-tag-plugins is a collection of plugins that connect the Claude coding agent to SaaS services such as task trackers, databases, monitoring systems, and document platforms. Each plugin focuses on one service, so workspaces can enable the integrations they use.
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 anthropics/claude-tag-plugins --skill hubspot-apigit clone --depth 1 https://github.com/anthropics/claude-tag-pluginsWrote 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/anthropics/claude-tag-plugins/hubspot-api)<a href="https://agentmods.dev/skills/anthropics/claude-tag-plugins/hubspot-api"><img src="https://agentmods.dev/badge/skills/anthropics/claude-tag-plugins/hubspot-api.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 | $0.00122 | $0.03796 |
| Opus 5 | $0.00061 | $0.01898 |
| Sonnet 5 | $0.00024 | $0.00759 |
| Haiku 4.5 | $0.00012 | $0.00380 |
Grade A, and why
hubspot-api scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS "https://api.hubapi.com/crm/v3/objects/contacts?limit=1" \ How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HubSpot's CRM API (v3) is uniform across object types: every object lives under https://api.hubapi.com/crm/v3/objects/{objectType} and supports the same basic/search/batch/association operations.
(HubSpot is rolling out date-based path versions — /crm/objects/2026-03/... — as the successor naming. The v3/v4 paths below all still work; HubSpot has announced v4 becomes unsupported on 2027-03-30 and v3's end-of-support date is not yet set. No migration is required for now.)
Key concepts:
- Object types are identified by name (
contacts,companies,deals,tickets) or by numericobjectTypeId(0-1,0-2,0-3,0-5). Custom objects are2-<n>or theirp_<name>alias. Either form works in the URL. - Properties are opt-in on reads. List/get calls return only a handful of default properties
(
hs_object_id,createdate,lastmodifieddate, and per-type defaults likeemail/firstnamefor contacts). Always passproperties=with a comma-separated list of the fields you actually need, or you'll get records that look empty. - Each object type has its own primary display property and dedup key. Contacts dedup on
email; companies ondomain; deals and tickets have no dedup. Know the key before creating. - Associations are typed. The common ones (
contact_to_company,deal_to_contact, etc.) have built-in type IDs. You can also define custom association labels.
Request setup
Authentication is handled by the runtime — credentials are injected into outbound requests to this
API, so there is nothing to set up. Do not try to create, mint, refresh, or validate tokens or keys.
Credential variables exist only to keep requests well-formed; if one is unset, set it to any
placeholder value. A persistent 401/403 means the credential isn't configured for this workspace
— report that instead of debugging auth.
Every request carries a bearer header. The configured credential has a set of scopes
(crm.objects.contacts.read, crm.objects.deals.write, etc.) that control what it can touch.
export HUBSPOT_ACCESS_TOKEN="placeholder" # injected by the runtime; any value works
Sanity check — confirm the workspace is wired up:
curl -sS "https://api.hubapi.com/crm/v3/objects/contacts?limit=1" \
-H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}" | jq .
A 403 means the request authenticated but the configured credential lacks the scope for what you
tried.
For brevity the recipes below use a helper. Define it once, or copy the -H flag onto each curl:
hsapi() { curl -sS "$@" -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}" -H "Content-Type: application/json"; }
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.
- 7d ago First seen · 294 lines · 122 tokens per session scan A 9a1cf0eb6971
hubspot-api is a skill published in the GitHub repository anthropics/claude-tag-plugins (47 stars, last pushed 3d ago), licensed Apache-2.0. It adds 122 tokens to every session and 3,796 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…