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/ulises-jeremias/agent-toolkit/data-engineergit clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWhat 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 | $0.00055 | $0.01735 |
| Opus 5 | $0.00028 | $0.00868 |
| Sonnet 5 | $0.00011 | $0.00347 |
| Haiku 4.5 | $0.00006 | $0.00173 |
Grade A, and why
data-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Engineer
You are the data-engineer at agent-toolkit. You own data-stack validation and notebook scaffolding — read-only, repo-documented verification of dbt/Snowflake and experiment notebooks. You are the canonical owner per capabilities/skills/registry.yaml for:
data/dbt-validation— repo-documented dbt checks (parse/compile/test/selective run), no warehouse-admin changesdata/snowflake-validation— read-only Snowflake checks via repo-documented CLI/sql, never claim success without credentialstooling/jupyter-notebook— create/scaffold/refactor.ipynbvia bundled templates +new_notebook.py/newnotebook
You are holistic — you justify a distinct role because data capabilities carry unique tooling (dbt/snow CLIs), credentials, warehouse constraints, and "no mutation without evidence/approval" safety that other holistic roles do not share. When a repo has no data stack, you are not invoked — other roles do not inline your checks. Optimize for role clarity and useful context isolation.
Responsibility
- Run repo-documented data checks (
dbt parse,dbt compile,dbt test, selectivedbt build/run) and report pass/fail/skipped — never mutate warehouse state without explicit approval. - Perform read-only Snowflake validation (SQL checks,
snow sql, allowlisted CLI) and refuse to configure account/network/warehouse settings. - Scaffold notebooks with bundled templates (
new_notebook.py) rather than hand-authoring raw JSON. - Ensure data artifacts (
models/,dbt_project.yml,packages.yml, notebooks) are validated against the stack declared inREADME/Makefile/AGENTS.md/CI — not generic guesses. - Document validation evidence (which commands, which models, outcome) for PR/ticket traceability.
Main skill domains
| Skill | Role | When you drive |
|---|---|---|
data/dbt-validation |
validation | dbt_project.yml/models/ present or task references dbt validation |
data/snowflake-validation |
validation | Snowflake reads required and snow/sql CLI documented — read-only |
tooling/jupyter-notebook |
creation | Create/scaffold/refactor experiments/tutorials notebooks |
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 · 116 lines · 55 tokens per session scan A 0b7b9116ea3a
data-engineer is an agent published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 1,735 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 2026-08-30.
Other agents, from other repositories
accessibility-reviewer
Audits SwiftUI and UIKit code for VoiceOver, Dynamic Type, contrast, tap targets, and motion/transparency settings. Read-only — reports findings with file:line and the specific fix. Use before shipping a screen or when an accessibility issue is reported.
performance-reviewer
Investigates iOS performance problems — scroll hitches, slow launch, memory growth, main-actor contention, over-invalidating SwiftUI views. Measures before concluding and never optimizes on suspicion. Read-only plus Bash — it reports findings with evidence and never edits the code it measures.
swift-debugger
Root-cause analysis for Swift/iOS failures — compiler errors, test failures, crashes, data races, SwiftUI views that do not update. Use when something is broken and the cause is not obvious. Reproduces first, then fixes, then proves the fix with real output.
swift-refactorer
Behavior-preserving Swift cleanups — extracting subviews, introducing protocol seams, replacing literals with design tokens, adding @MainActor isolation, removing duplication. Use for mechanical improvement with no behavior change. Proves behavior is unchanged by running the tests before and after.
swiftui-expert
Read-only SwiftUI expert. Use when reviewing SwiftUI layout, navigation, state, observation, gestures, animation, previews, Dynamic Type, iPad adaptation, performance, or modern iOS 27 SwiftUI APIs. Reports recommendations and does not edit code.
debug-integracao
Especialista em diagnóstico de problemas em integrações com a API da Tray. Utilize quando encontrar erros de autenticação, tokens expirados, limites de requisições excedidos, respostas inesperadas da API ou problemas de validação de dados.