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/altimateai/data-engineering-skills/debugging-dbt-errorsnpx skills add AltimateAI/data-engineering-skills --skill debugging-dbt-errorsgit clone --depth 1 https://github.com/AltimateAI/data-engineering-skillsWhat 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 | $0.00112 | $0.01050 |
| Opus 5 | $0.00056 | $0.00525 |
| Sonnet 5 | $0.00022 | $0.00210 |
| Haiku 4.5 | $0.00011 | $0.00105 |
Grade A, and why
debugging-dbt-errors 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 2d 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:
- debugging-dbt-errors — 92% identical, 11 lines differ
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dbt Troubleshooting
Read the full error. Check upstream first. ALWAYS run dbt build after fixing.
Critical Rules
- ALWAYS run
dbt buildafter fixing - compile is NOT enough to verify the fix - If fix fails 3+ times, stop and reassess your entire approach
- Verify data after build - build passing doesn't mean output is correct
Workflow
1. Get the Full Error
dbt compile --select <model_name>
# or
dbt build --select <model_name>
Read the COMPLETE error message. Note the file, line number, and specific error.
2. Inspect Actual Data (For Data Issues)
Before fixing "wrong output" or "incorrect results", query the actual data:
# Preview current output
dbt show --select <model_name> --limit 20
# Check specific values with inline query
dbt show --inline "select * from {{ ref('model_name') }} where <condition>" --limit 10
# Compare with expected - look for patterns
dbt show --inline "select column, count(*) from {{ ref('model_name') }} group by 1 order by 2 desc" --limit 10
Understand what's wrong before attempting to fix it.
3. Read Compiled SQL
cat target/compiled/<project>/<path>/<model_name>.sql
See the actual SQL that will run.
4. Analyze Error Type
| Error Type | Look For |
|---|---|
| Compilation Error | Jinja syntax, missing refs, YAML issues |
| Database Error | Column not found, type mismatch, SQL syntax |
| Dependency Error | Missing model, circular reference |
5. Check Upstream Models
# Find what this model references
grep -E "ref\(|source\(" models/<path>/<model_name>.sql
# Read upstream model to verify columns
cat models/<path>/<upstream_model>.sql
Many errors come from upstream changes, not the current model.
6. Apply Fix
Common fixes:
| Error | Fix |
|---|---|
| Column not found | Check upstream model's output columns |
| Ambiguous column | Add table alias: table.column |
| Type mismatch | Add explicit CAST() |
| Division by zero | Use NULLIF(divisor, 0) |
| Jinja error | Check matching {{ }} and {% %} |
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.
- 2d ago First seen · 154 lines · 112 tokens per session scan A 3a32473f71da
debugging-dbt-errors is a skill published in the GitHub repository AltimateAI/data-engineering-skills (122 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 1,050 once invoked, about $0.0006 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
pr-verify
Verify a Docglow change actually works before submitting or merging a PR. Runs the conformance suite, then a behavioral verification pass (flag matrix, artifact-join spot checks, pipeline contract sweep, payload budget). Use when reviewing a PR, self-reviewing a branch before opening a PR, or when asked to "verify…
animation-best-practices
CSS and UI animation patterns for responsive, polished interfaces. Use when implementing hover effects, tooltips, button feedback, transitions, or fixing animation issues like flicker and shakiness.
dbt-doctor
Static analysis and health checks for dbt projects. Use before committing SQL/YAML or when enforcing CI quality gates.
datahub-verified-remediation
Use this skill when a source schema change has broken, or is about to break, a downstream transformation and the user wants a fix they can merge — not a summary. Triggers on: "a column was renamed, fix the dbt model", "this field is gone downstream", "schema drift", "our model still selects the old column", "generate…
Data Pipeline Architect
Design and implement robust data pipelines — ETL/ELT, streaming, batch processing. From architecture to code with Airflow, dbt, Kafka, and modern data stack.
weekly-report
Generate recurring weekly or monthly analytics reports with period-over-period comparison, anomaly detection, and executive summaries. Use when the user asks for a weekly report, monthly KPI review, recurring metrics snapshot, or needs automated period-over-period diffing. Saves templates for one-command re-runs.