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 agentmods add skills/ericrisco/rsc-harness/duckdbnpx skills add ericrisco/rsc-harness --skill duckdbgit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/ericrisco/rsc-harness/duckdb)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/duckdb"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/duckdb.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 | $0.00085 | $0.02702 |
| Opus 5 | $0.00043 | $0.01351 |
| Sonnet 5 | $0.00017 | $0.00540 |
| Haiku 4.5 | $0.00009 | $0.00270 |
Grade C, and why
duckdb scanned grade C with 2 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 3d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl https://install.duckdb.org | sh # or: brew install duckdb Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl https://install.duckdb.org | sh # or: brew install duckdb How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DuckDB — embedded columnar OLAP, no server
DuckDB is an in-process analytical (OLAP) database: it links into your process like SQLite, but stores
data column-by-column and vectorizes execution for aggregates, joins, and window functions. There is no
server, no port, no daemon — you pip install duckdb (or drop one CLI binary) and query. Its killer move
is reading Parquet/CSV/JSON/Arrow in place, without a load step, so a folder of files becomes a table.
The fact that drives every routing decision below: DuckDB is one writer, many readers, single process. It is brilliant for analysis on one machine and wrong for multi-user serving or transactional app writes.
Latest stable is v1.5.3 (released 2026-05-20). Pin the LTS line (v1.4.x; v1.4.4 LTS shipped 2026-01-26) for anything long-lived — LTS gets ~1 year of patches and a stable storage format. Use 1.5.x for greenfield exploration.
Is DuckDB the tool? (decide first)
| Your workload | Reach for |
|---|---|
| Analytics over local/remote files, one process, one writer | duckdb (this skill) |
| Many concurrent users, production query API, dashboards-as-a-service, petabyte scale | clickhouse-analytics |
| App transactional CRUD: users, orders, many small writes, FKs, connection pool | postgresdb |
| Embedded single-file transactional store / edge / sync | sqlite-turso |
| Pure SQL syntax question, engine-agnostic (window fns, CTEs) | sql |
| Similarity / embedding search as the core workflow | vector-db |
The two you will confuse most: DuckDB vs ClickHouse is embedded-single-node vs server-distributed — under ~10GB on one box DuckDB usually wins; pick ClickHouse when many people query concurrently. DuckDB vs SQLite is same niche, opposite workload — both embedded single-file, but SQLite is row-store OLTP and DuckDB is column-store OLAP. Don't run your app's writes through DuckDB.
What ships with it
5 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.
- 3d ago First seen · 203 lines · 85 tokens per session scan C 4c0ab72c7f66
duckdb is a skill published in the GitHub repository ericrisco/rsc-harness (65 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 2,702 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
duckdb
Operational skill for DuckDB: local analytical SQL, Parquet/CSV scans, views, and zero-copy handoff to pandas/Polars.
analytical-databases-expert
Design and query columnar analytical stores: DuckDB, ClickHouse and cloud warehouses, including file formats, partitioning, sort keys and cost control. Use when the user mentions DuckDB, ClickHouse, Parquet, columnar storage, OLAP, a data warehouse or lakehouse, analytical queries over large tables, or when the task…
chdb-datastore
Use when the user has tabular data (pandas DataFrame, parquet, csv, Arrow, json) and wants to filter, group, aggregate, join, or speed up slow pandas. Provides chDB DataStore — same pandas API, ClickHouse engine underneath. Also handles reading from S3, MySQL, PostgreSQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake…
chdb-sql
Use when the user wants to run SQL — especially analytical SQL — on local files (parquet/csv/json), URLs, S3 paths, or remote databases (Postgres, MySQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake) without setting up a server. Provides chDB — embedded ClickHouse SQL in Python with 1000+ functions, Session for…
clickhouse
Operational skill for ClickHouse: MergeTree tables, partitions, projections, ingest, and analytical SQL performance.
moai-domain-database
Database specialist covering PostgreSQL, MongoDB, Redis, Oracle, and cloud database platforms (Neon, Supabase, Firestore). Use for schema design, query optimization, indexing strategies, data modeling, or cloud database selection. Cloud vendor guide absorbed from moai-platform-database-cloud.