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 hicham-bab/dbt-legacy-migration-skills --skill migrating-datastage-to-dbtgit clone --depth 1 https://github.com/hicham-bab/dbt-legacy-migration-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/hicham-bab/dbt-legacy-migration-skills/migrating-datastage-to-dbt)<a href="https://agentmods.dev/skills/hicham-bab/dbt-legacy-migration-skills/migrating-datastage-to-dbt"><img src="https://agentmods.dev/badge/skills/hicham-bab/dbt-legacy-migration-skills/migrating-datastage-to-dbt/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/hicham-bab/dbt-legacy-migration-skills/migrating-datastage-to-dbt"><img src="https://agentmods.dev/badge/skills/hicham-bab/dbt-legacy-migration-skills/migrating-datastage-to-dbt.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 | $0.00103 | $0.04575 |
| Opus 5.5 | $0.00041 | $0.01830 |
| Sonnet 5.5 | $0.00021 | $0.00915 |
| Haiku 4.5 | $0.00010 | $0.00458 |
Grade A, and why
migrating-datastage-to-dbt 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 today.
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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrating IBM DataStage to dbt
This skill migrates an IBM InfoSphere DataStage parallel job (a .dsx export) into a governed dbt
project — reproducing the transformation logic as dbt models, snapshots, and macros with tests,
docs, and contracts, then proving parity against warehouse data.
The core approach: DataStage is an engine-executed ETL tool — the DataStage Parallel Engine runs each job's stage graph itself (Join, Filter, Transformer, Aggregator, Sort, Lookup, Merge, Funnel, Remove Duplicates, Surrogate Key Generator, Change Capture/Apply…), usually reading/writing flat files or datasets between stages. Unlike a push-down ELT tool, a DataStage job's logic doesn't already live as warehouse SQL — it has to be re-authored as SQL, the same kind of job as an Informatica PowerCenter mapping. We inventory every job's stage graph, translate stage-by-stage using the stage answer key, validate each output against the warehouse, and report coverage and cost.
Scope — what maps and what doesn't:
- Parallel jobs (real ETL stage graphs) → dbt models. This is the migratable workload and the coverage denominator.
- Job Sequences (orchestration/control-flow: run this job then that one, retry, email on
failure) → mostly out of dbt scope.
Job Activitysteps become the dbt DAG/run; branching, retries, and notifications move to a scheduler/platform job. Document these; do not force them into models.
Success criteria: Migration is complete when:
dbt compilefinishes with 0 errors and 0 warnings- Every generated model builds (
dbt build) and its tests pass - Data parity is proven for each mart (row-for-row or aggregate baseline — see Step 5)
- ≥95% of the inventoried transformation stages are migrated and validated, with the residual (and the out-of-scope orchestration pieces) explicitly listed
Validation cost: dbt compile is the free iteration gate. Only dbt build, dbt test, and
the parity queries touch the warehouse — run those after compile is clean.
This skill shares its workflow with the legacy-to-dbt-migration-foundations skill; steps below
link into its references for the common work. Assume the migrator may be new to dbt — explain
each dbt concept (materializations, incremental, snapshots, contracts, Fusion) in plain language as
it comes up (foundations → dbt-concepts-explained.md), and explain the reason behind each choice,
not just the mechanics.
What ships with it
3 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.
- today First seen · 319 lines · 103 tokens per session scan A 7e662399b47f
migrating-datastage-to-dbt is a skill published in the GitHub repository hicham-bab/dbt-legacy-migration-skills (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 103 tokens to every session and 4,575 once invoked, about $0.0004 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 2026-10-02.
Other skills, from other repositories
pinecone
Managed vector DB for production RAG and search.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
ingesting-into-data-lake
Import data into the AWS data lake from S3 files, local uploads, JDBC databases (Oracle, SQL Server, PostgreSQL, MySQL, RDS, Aurora), Amazon Redshift, Snowflake, BigQuery, DynamoDB, or existing Glue catalog tables (migration). Default target is S3 Tables; standard Iceberg on a general purpose bucket is supported where…
graphjin-env
Use when setting up a training or evaluation loop against a GraphJin agent environment — running the container, reading /health, driving episodes hosted or step-by-step or with your own agent over MCP, splitting train from eval, exporting trajectories, and deciding whether two rewards can be compared.
qdrant-search-quality-diagnosis
Diagnoses Qdrant search quality issues. Use when someone reports 'results are bad', 'wrong results', 'not relevant results', 'missing matches', 'recall is low', 'approximate search worse than exact', 'which embedding model', 'quality dropped after quantization', 'how to measure retrieval quality', 'build a golden…
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.