systematic-debug

systematic-debug is a skill for Claude Code, Codex from adityawrk/analytics-with-claude-code. It costs 64 tokens per session (1,856 once invoked), scanned A, original, MIT.

A step-by-step method for finding and fixing broken queries, data pipelines, dbt models, or analysis code. It requires reproducing the problem, studying the evidence, making one change at a time, and checking the result.

In plain words
What is it for?
Use it to investigate failed queries, broken data pipelines, dbt model errors, and unexpected analytical results.
Why use it?
It prevents guesswork and makes it clear which change fixed the problem. After three failed attempts, it stops and summarizes what was learned instead of continuing to guess.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/adityawrk/analytics-with-claude-code/systematic-debug
Any agent
npx skills add adityawrk/analytics-with-claude-code --skill systematic-debug
Clone the repo
git clone --depth 1 https://github.com/adityawrk/analytics-with-claude-code

Made for: Claude Code, Codex.

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.

agentmods badge for systematic-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/adityawrk/analytics-with-claude-code/systematic-debug.svg)](https://agentmods.dev/skills/adityawrk/analytics-with-claude-code/systematic-debug)
Your own site
<a href="https://agentmods.dev/skills/adityawrk/analytics-with-claude-code/systematic-debug"><img src="https://agentmods.dev/badge/skills/adityawrk/analytics-with-claude-code/systematic-debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,856 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00064 $0.01856
Opus 5 $0.00032 $0.00928
Sonnet 5 $0.00013 $0.00371
Haiku 4.5 $0.00006 $0.00186

Measured 4d ago against content hash c5555331b000, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

systematic-debug 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 4d 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/skills/systematic-debug/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systematic Debugging for Analytics

A 4-phase structured debugging methodology. Follow these phases in strict order. No shortcuts. No cargo-cult debugging. No "just try this and see."


Ground Rules

Read these first. They are non-negotiable.

  1. NEVER skip Phase 1. Do not attempt a fix before reproducing the error and reading the full output. No exceptions.
  2. NEVER make multiple changes at once. One variable at a time. If you change two things and the problem goes away, you do not know which one fixed it.
  3. 3-Strike Rule. After 3 failed fix attempts, STOP. Summarize what you have tried, what you have learned, and escalate to the user. Do not keep guessing.
  4. State your hypothesis. Before every fix attempt, tell the user what you believe is wrong and why. "I think X because Y, so I will try Z."
  5. Clean up after yourself. Remove all debug instrumentation (extra logging, LIMIT clauses, temp tables, print statements) before declaring the issue resolved.

Phase 1: Reproduce and Gather Evidence

Goal: See the failure with your own eyes. Understand exactly what is happening before forming any opinion about why.

Steps

  1. Run the failing query or script exactly as reported.

    • Use the same database, schema, and role if possible.
    • Do not modify the query before running it.
    • Capture the full error output — not just the first line.
  2. Read the complete error message.

    • Copy the full stack trace or error output.
    • Identify the specific line, column, or object that failed.
    • Note the error code if one is provided.
  3. Check the environment.

    • What database/warehouse is this running against?
    • What schema or dataset is active?
    • Are there any session-level settings (timezone, role, warehouse size)?
  4. Check data freshness. (Analytics-specific)

    • When was the source data last updated?
    • Is the failure caused by stale or missing data rather than a code bug?
    • Run SELECT MAX(updated_at) or equivalent on key source tables.

Read the full file on GitHub · 197 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.

  1. 4d ago First seen · 197 lines · 64 tokens per session scan A c5555331b000

Subscribe to this mod's changes

systematic-debug is a skill published in the GitHub repository adityawrk/analytics-with-claude-code (5 stars, last pushed 6mo ago), licensed MIT. It adds 64 tokens to every session and 1,856 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.

Related

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…

docglow/docglow · 79 tokens

developing-incremental-models

Develops and troubleshoots dbt incremental models. Use when working with incremental materialization for: (1) Creating new incremental models (choosing strategy, uniquekey, partition) (2) Task mentions "incremental", "append", "merge", "upsert", or "late arriving data" (3) Troubleshooting incremental failures (merge…

AltimateAI/data-engineering-skills · 112 tokens

altimate-code

Delegates dbt and warehouse work to altimate-code, a specialized CLI agent with 100+ purpose-built data tools. USE THIS SKILL FIRST whenever the task mentions or implies: warehouse access (Snowflake, BigQuery, Redshift, Databricks, Postgres, MySQL, DuckDB), column-level lineage, downstream-impact analysis, dbt builds…

AltimateAI/data-engineering-skills · 0 tokens

debugging-dbt-errors

Debugs and fixes dbt errors systematically. Use when working with dbt errors for: (1) Task mentions "fix", "error", "broken", "failing", "debug", "wrong", or "not working" (2) Compilation Error, Database Error, or test failures occur (3) Model produces incorrect output or unexpected results (4) Need to troubleshoot…

AltimateAI/data-engineering-skills · 112 tokens

documenting-dbt-models

Documents dbt models and columns in schema.yml. Use when working with dbt documentation for: (1) Adding model descriptions or column definitions to schema.yml (2) Task mentions "document", "describe", "description", "dbt docs", or "schema.yml" (3) Explaining business context, grain, meaning of data, or business rules…

AltimateAI/data-engineering-skills · 105 tokens

refactoring-dbt-models

Safely refactors dbt models with downstream impact analysis. Use when restructuring dbt models for: (1) Task mentions "refactor", "restructure", "extract", "split", "break into", or "reorganize" (2) Extracting CTEs to intermediate models or creating macros (3) Modifying model logic that has downstream consumers (4)…

AltimateAI/data-engineering-skills · 108 tokens