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 Kilo-Org/kilo-marketplace --skill apache-hudi-lakehousegit clone --depth 1 https://github.com/Kilo-Org/kilo-marketplaceWrote 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/kilo-org/kilo-marketplace/apache-hudi-lakehouse)<a href="https://agentmods.dev/skills/kilo-org/kilo-marketplace/apache-hudi-lakehouse"><img src="https://agentmods.dev/badge/skills/kilo-org/kilo-marketplace/apache-hudi-lakehouse/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/kilo-org/kilo-marketplace/apache-hudi-lakehouse"><img src="https://agentmods.dev/badge/skills/kilo-org/kilo-marketplace/apache-hudi-lakehouse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00043 | $0.01203 |
| Opus 5 | $0.00022 | $0.00602 |
| Sonnet 5 | $0.00009 | $0.00241 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
apache-hudi-lakehouse 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- apache-hudi-lakehouse — 89% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apache Hudi Lakehouse
Overview
Use this skill when Apache Hudi is the primary table layer for incremental lakehouse workloads. It helps agents reason about mutation-heavy patterns, table type selection, compaction behavior, timeline safety, and consumer expectations across read-optimized and real-time query paths.
When to Use
- choosing or operating
Apache Hudifor lakehouse tables - building record-level upsert or delete pipelines
- managing compaction, clustering, and incremental consumption
- supporting lakehouse tables with heavy mutations (CDC sinks, slowly changing dimensions)
- planning multi-engine access (Spark, Presto, Trino, Athena, Hive)
Do not use this when the workload is append-only with no mutation requirements and simpler formats like Parquet or Iceberg would suffice.
Workflow
-
Define mutation patterns and read access expectations. Include:
- primary record key and partition path
- expected operations: inserts, upserts, deletes, or bulk replaces
- read latency expectations: are readers okay with merge-on-read or do they need read-optimized snapshots?
- query engines that must access the table
- expected write throughput and record mutation rate
-
Choose the right table type and indexing strategy.
Copy-on-Write (COW): best for read-heavy workloads, produces columnar snapshots on writeMerge-on-Read (MOR): best for write-heavy workloads, defers merge to read time or compaction- choose record index type:
BLOOM,GLOBAL_BLOOM,SIMPLE,BUCKET, orRECORD_INDEX - index choice affects upsert performance and scaling behavior
- document why the table type was chosen — revisiting later is expensive
-
Plan compaction and clustering explicitly.
- for MOR tables: compaction converts log files to columnar — it is not optional
- define compaction strategy: synchronous (inline) or asynchronous (scheduled)
- set compaction triggers: by number of commits, time, or log file size
- clustering reorganizes data layout for query performance — plan separately from compaction
- budget compute for compaction and clustering in cost planning
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.
- 12d ago First seen · 106 lines · 43 tokens per session scan A 454852f0b8cb
apache-hudi-lakehouse is a skill published in the GitHub repository Kilo-Org/kilo-marketplace (175 stars, last pushed 22d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,203 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
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…