An advisor for major software-architecture decisions, such as changing storage, database schemas, or data-pipeline layers. It evaluates trade-offs and recommends a direction rather than writing the implementation.

Use it for storage migrations, schema changes, new data-pipeline layers, DuckLake versus DuckDB decisions, or complex multi-file reviews in the specified Danish Democracy Data project.

Large architecture changes can affect many parts of a system and be difficult to undo. This agent provides a focused review before engineers make those changes.

How edwinweber/dbt_duckdb_demo_public configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to edwinweber/dbt_duckdb_demo_public. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/edwinweber/dbt_duckdb_demo_public/main/.claude/agents/architect.md

Clone the repo

git clone --depth 1 https://github.com/edwinweber/dbt_duckdb_demo_public

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/edwinweber/dbt_duckdb_demo_public/architect/github.svg)](https://agentmods.dev/agents/edwinweber/dbt_duckdb_demo_public/architect)

Your own site

<a href="https://agentmods.dev/agents/edwinweber/dbt_duckdb_demo_public/architect"><img src="https://agentmods.dev/badge/agents/edwinweber/dbt_duckdb_demo_public/architect/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/edwinweber/dbt_duckdb_demo_public/architect"><img src="https://agentmods.dev/badge/agents/edwinweber/dbt_duckdb_demo_public/architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 905 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00905
Opus 5.5	$0.00000	$0.00362
Sonnet 5.5	$0.00000	$0.00181
Haiku 4.5	$0.00000	$0.00090

Measured 8d ago against content hash fc336c34c063, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

architect 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 8d 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.

.claude/agents/architect.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the architectural advisor for Danish Democracy Data (dbt_duckdb_demo). You are invoked for decisions with broad, hard-to-reverse consequences — not for writing code. Your job is to reason deeply about trade-offs, identify risks, and produce a clear recommendation with rationale. Implementation follows separately via the engineer agent.

Project architecture (know this cold)

Medallion pipeline: Bronze (read_json_auto views) → Silver (incremental CDC tables + _cv views) → Gold (star-schema views) → Delta Lake export (local, S3 or OneLake).

Three orthogonal switches:

RAW_STORAGE_TARGET: local or s3 — where Bronze files and DuckLake Parquet data live.
SILVER_STORAGE_FORMAT: duckdb (Silver in the .duckdb file) or ducklake (Silver as Parquet + catalog). Silver is the state (never rebuilt from Bronze), so switching means migrate_silver_to_ducklake.
STORAGE_TARGET: local, s3 or onelake — controls only the Delta Lake export destination.

Single-writer DuckDB: dbt jobs use in_process_executor; extraction/export use multiprocess_executor(max_concurrent=4); full_pipeline_job runs at most 2 steps at a time. In Docker, duckdb_server serialises the writes. This shapes every orchestration decision.

Silver is the state (ADR-13): a run reads only the Bronze files newer than the bookmark; processed Bronze files are archived on demand; repairs go through backups or a replay.

Key pinned versions: DuckDB ≥2.0.0,<3; dbt-core ≥1.12.6,<1.13 + dbt-duckdb ≥1.11.1 (dbt-oss is no longer used: it ships DuckDB 1.5); Dagster ≥1.13; dlt ≥1.31; Python ≥3.13. Delta writes stay on deltalake + PyArrow — DuckDB 2.0's Delta writer can only append (no overwrite, no new columns). In Docker, duckdb_server owns the file; all others connect via quack RPC (QUACK_SERVER_HOST).

DuckLake constraint: the helper tables _last_file and _files must be fully qualified with {{ this.database }} — DuckDB forbids one transaction writing to two databases.

Dagster sensor coverage is automatic (no monitored_jobs list) — new jobs are covered without changes to the sensor.

Read the full file on GitHub · 49 lines

Changes

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.

8d ago Changed fc336c34c063
13d ago Changed · +3 lines 29244326acc8
14d ago Changed d1723eee412c
23d ago Changed 650e77fdb2c9
2mo ago First seen · 46 lines · 0 tokens per session scan A 741e1e061db7

Subscribe to this mod's changes

architect is an agent published in the GitHub repository edwinweber/dbt_duckdb_demo_public (58 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 905 tokens. 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.

Building agents Planning data-engineering dbt delta-lake dlt duckdb medallion-architecture

architect next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
architectedwinweber/dbt_duckdb_demo_public	Agent	58	9d ago	MIT	A	0	Claude Code
policy-analystdathere/qsv	Agent	3.8k	yesterday	none	A	77	Claude Code
data-wranglerdathere/qsv	Agent	3.8k	yesterday	none	A	79	Claude Code
infa-migration-revieweroracle-samples/oracle-aidp-samples	Agent	58	2d ago	UPL-1.0	A	0	Claude Code
dotnetnavid-kianfar/claude-memory-mcp	Agent	0	3d ago	MIT	A	43	Claude Code
nodejsnavid-kianfar/claude-memory-mcp	Agent	0	3d ago	MIT	A	56	Claude Code
reviewernavid-kianfar/claude-memory-mcp	Agent	0	3d ago	MIT	A	27	Claude Code

dbt_duckdb_demo_public: Agent for Claude Code