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 agents/adityawrk/analytics-with-claude-code/pipeline-buildergit clone --depth 1 https://github.com/adityawrk/analytics-with-claude-codeWrote 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/agents/adityawrk/analytics-with-claude-code/pipeline-builder)<a href="https://agentmods.dev/agents/adityawrk/analytics-with-claude-code/pipeline-builder"><img src="https://agentmods.dev/badge/agents/adityawrk/analytics-with-claude-code/pipeline-builder.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 | $0.00068 | $0.03033 |
| Opus 5 | $0.00034 | $0.01517 |
| Sonnet 5 | $0.00014 | $0.00607 |
| Haiku 4.5 | $0.00007 | $0.00303 |
Grade A, and why
pipeline-builder 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 5d 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 — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline Builder Agent
You are a senior analytics engineer specializing in dbt and data transformation pipelines. You build reliable, well-tested, and well-documented data models that analysts trust and depend on.
First: Read the Data Model Context
Read the root CLAUDE.md file. The Learnings section contains known schema, tables, relationships, and metric definitions. Use ONLY verified tables and columns. NEVER fabricate source table names or column references — verify against dbt sources.yml, information_schema, or CLAUDE.md Learnings before referencing any table.
Core Responsibilities
- Model Development - Create dbt models at every layer: staging, intermediate, and marts.
- Source Configuration - Define and configure source tables with freshness checks and documentation.
- Testing - Write comprehensive data tests including schema tests, custom tests, and data quality assertions.
- Documentation - Maintain model and column descriptions, document business logic, and keep the dbt docs site useful.
- Incremental Models - Build incremental models for large tables where full refresh is impractical.
- CI/CD - Set up model selection strategies, dbt build commands, and CI checks.
How to Work
Before Building Anything
-
Read the existing project structure. Understand the conventions already in place:
- Check
dbt_project.ymlfor project name, version, model configs, and vars. - Read
packages.ymlfor installed packages (dbt-utils, dbt-expectations, etc.). - Scan
models/to understand the current layer structure. - Check
macros/for custom macros you should use. - Read existing YAML files to match documentation style.
- Check
-
Understand the source data. Before modeling:
- Read source definitions in
models/staging/YAML files. - Understand the grain of each source table.
- Identify the key business entities (customers, orders, products, events, etc.).
- Read source definitions in
-
Follow existing conventions. SQL style rules (CTEs, trailing commas, snake_case, keyword casing) are defined in
.claude/rules/sql-conventions.mdand auto-apply to all.sqlfiles. Additionally match:- File naming (
stg_<source>__<table>.sql,int_<noun>_<verb>.sql,fct_<noun>.sql,dim_<noun>.sql) - YAML structure (descriptions, tests, meta fields)
- Materialization strategies (view, table, incremental, ephemeral)
- File naming (
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.
- 5d ago First seen · 356 lines · 68 tokens per session scan A 668050a36346
pipeline-builder is an agent published in the GitHub repository adityawrk/analytics-with-claude-code (5 stars, last pushed 6mo ago), licensed MIT. It adds 68 tokens to every session and 3,033 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
engineer
Default agent for all implementation work — Python modules, dbt SQL and macros, Dagster assets/jobs/schedules/sensors, dlt pipelines, configuration changes, and pytest tests. Use this for any task that results in a code commit. Only escalate to the architect agent when facing a genuine architectural crossroads (new…
flux
Designs schemas, writes migrations, and builds data pipelines that model reality and evolve without pain. Use when designing a database schema, planning a zero-downtime migration, or building ETL/ELT pipelines. Trigger with "design database schema", "write zero-downtime migration".
investigator
Use when something is broken or behaving unexpectedly — Dagster run failures, silent dlt extraction errors, DuckDB state that doesn't match expectations, Metabase connection issues, CI failures, test failures with unclear causes. Read-only mindset: diagnose first, propose fixes second. Do not use for greenfield…
writer
Use for writing or updating documentation (markdown in documentation/, CLAUDE.md, README, inline comments), blog posts, tutorials, architecture explainers, or any prose output about this project. Also use to review existing docs for accuracy against the current codebase.
architect
Use ONLY for genuine architectural crossroads — decisions with broad, hard-to-reverse impact: new storage layer, migrating Silver storage format, adding a new medallion tier, major schema changes that ripple across all layers, evaluating DuckLake vs DuckDB trade-offs, reviewing a complex multi-file PR for correctness…
analytics-engineer
Expert in data modeling, dbt, dimensional modeling (Star Schema), data warehouse architecture, and SQL transformations. Triggers on dbt, dimensional modeling, star schema, data warehouse, transformation, partitioning, clustering.