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 estuary/agent-skills --skill materialize-hubspot-creategit clone --depth 1 https://github.com/estuary/agent-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/estuary/agent-skills/materialize-hubspot-create)<a href="https://agentmods.dev/skills/estuary/agent-skills/materialize-hubspot-create"><img src="https://agentmods.dev/badge/skills/estuary/agent-skills/materialize-hubspot-create/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/estuary/agent-skills/materialize-hubspot-create"><img src="https://agentmods.dev/badge/skills/estuary/agent-skills/materialize-hubspot-create.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 | $0.00078 | $0.04585 |
| Opus 5.5 | $0.00031 | $0.01834 |
| Sonnet 5.5 | $0.00016 | $0.00917 |
| Haiku 4.5 | $0.00008 | $0.00458 |
Grade A, and why
materialize-hubspot-create 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 — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create HubSpot Materialization
Create a HubSpot materialization using flowctl to write data from Estuary collections into HubSpot CRM objects.
Applies to: materialize-hubspot
This connector is a write-back connector — it's for pushing enriched or external data into HubSpot CRM records, not for general-purpose data warehousing. Common use case: enrich HubSpot contacts/companies with data computed elsewhere (product usage, lead scoring, support signals) and sync it back into HubSpot properties.
Known Limitations
- Non-unique match properties can create duplicate records. With a non-unique match property, the connector falls back to a search-based lookup to find existing records; concurrent writes against the same non-unique value can create two records for one logical entity instead of updating one. Treat a unique match property as a hard requirement, not a recommendation.
- An invalid enumeration value stops the whole materialization task, not just that record. The connector either writes the data as given or stops — it does not skip or drop an invalid value to keep the task running. All bound object types share one task, so one bad value on any binding halts every binding until it's resolved. Validate enum values upstream (e.g. in a derivation) before they reach this connector.
- Sensitive/Highly Sensitive HubSpot properties can't be written. Writing these fields requires OAuth scopes the connector doesn't request. There's no workaround short of not targeting those properties.
- Associations between CRM objects can't be materialized. Associations need a separate process (e.g. a HubSpot API call from a derivation, or workflow automation in HubSpot).
- Deleting a source row never deletes the HubSpot record. Hard deletes aren't supported. Track deletions via a
meta_opproperty instead (see Step 1.4). - Long/unusual field names can fail to map to the expected property, silently. The documented truncation rule for property names over 100 characters doesn't reliably match the resulting property name, and when the computed property name doesn't exist, the value is dropped with no error or warning. Spot-check any field with an unusual (long, digit-leading, special-character) name in HubSpot after publishing rather than trusting a clean task status.
- Round-trip pipelines (HubSpot capture → derivation → this materialization, writing back into HubSpot) carry a feedback-loop risk. The connector always runs in delta-update mode, so every document is written as given, and each write bumps the same
updatedAt/lastmodifieddatefield the HubSpot capture uses for incremental change detection. The capture can see the materialization's own write as a new change, re-feed it through the derivation, and write again — indefinitely, if the derivation's output is deterministic for unchanged inputs. For this pattern, use a stateful derivation that suppresses re-emission when only previously-written fields have changed: fingerprint the input fields the derivation actually reads, store it, and skip emitting when the fingerprint is unchanged. Seederivation-stateful-logic.
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 First seen · 308 lines · 78 tokens per session scan A 37449c93dd64
materialize-hubspot-create is a skill published in the GitHub repository estuary/agent-skills (7 stars, last pushed 26d ago), licensed Apache-2.0. It adds 78 tokens to every session and 4,585 once invoked, about $0.0003 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 2026-09-18.
Other skills, from other repositories
change-data-capture-admin
Use when enabling, configuring, or monitoring Change Data Capture (CDC) entity selection, channel enrichment, and delivery usage limits from an admin perspective. NOT for writing an Apex change-event trigger — use apex/change-data-capture-apex. NOT for subscribing an external system over Pub/Sub or CometD — use…
stream-processing-designer
Design a stream processing system for unbounded, continuously arriving data. Use when choosing a message broker (Kafka vs RabbitMQ), implementing change data capture (CDC) from PostgreSQL, MySQL, or MongoDB via Debezium or Maxwell, selecting window types for aggregation (tumbling, hopping, sliding, session), joining…
change-data-capture-admin
Use when enabling, configuring, or monitoring Change Data Capture (CDC) entity selection, channel enrichment, and delivery usage limits from an admin perspective. NOT for CDC Apex trigger implementation (use change-data-capture-integration).
target-connector
This skill should be used when creating a new target connector for CocoIndex to integrate with external systems. It provides guidance on implementing TargetHandler, TargetActionSink, and related types for declarative target state synchronization with change detection and automatic cleanup.
developing-kafka-python-client
Use when the user wants to build a Python Kafka producer or consumer, add Schema Registry to existing Python code, migrate from raw JSON to schema-backed serialization, or scaffold a confluent-kafka-python project for Confluent Cloud, local Docker, or WarpStream. Also use when user wants to optimize Python Kafka…
developing-kafka-java-client
Use when the user wants to integrate a Kafka client into an existing application or scaffold a Java Kafka client project (Maven or Gradle based) for Confluent Cloud, local Docker, or WarpStream. Covers the Apache Kafka Java clients (KafkaProducer/KafkaConsumer/KafkaShareConsumer) with Avro, JSON Schema, or Protobuf…