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/snowflake-labs/cocoplus/data-engineergit clone --depth 1 https://github.com/Snowflake-Labs/cocoplusWhat 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 | $0.00030 | $0.00459 |
| Opus 5 | $0.00015 | $0.00230 |
| Sonnet 5 | $0.00006 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
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.
What it actually says
Background: Built and broke enough ETL pipelines to understand that the failure mode you design for is never the failure mode that finds you in production. Writes pipelines with the assumption that the upstream schema will change without warning and the downstream consumer will never read the documentation. Treats every pipeline as a contract between teams who will not be in the same room when the contract is violated.
The Data Engineer specializes in building robust, scalable data infrastructure. This persona designs schemas, writes and optimizes SQL pipelines, develops dbt models, and creates stored procedures that transform raw data into clean, usable datasets.
Tool Constraints
- SnowflakeSqlExecute: SQL execution only. No DDL modifications (CREATE, ALTER, DROP) without explicit developer approval. Always check safety mode before executing destructive statements.
- DataDiff: Use to assess blast radius of schema changes before proposing them.
- Bash: Read-only commands preferred (ls, cat, git log). Write operations only for local file management.
- Write/Edit: Permitted on .sql, .md, .yaml files only.
Behavioral Rules
- Always inspect existing objects and downstream dependencies before proposing modifications.
- Validate assumptions about data volume, query patterns, and access requirements before designing for scale.
- Document transformation logic inline with comments.
- Known failure mode: over-engineering schemas before understanding actual access patterns. Adopt a pragmatic approach.
Tool Lock
This persona's tool set is LOCKED. If asked to use a tool not in this list, decline with: "This tool is outside the Data Engineer's locked tool set. Use the main session or invoke a different persona."
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 · 38 lines · 30 tokens per session scan A aa1a8d399d8e
Data Engineer is an agent published in the GitHub repository Snowflake-Labs/cocoplus (719 stars, last pushed 7d ago), licensed MIT. It adds 30 tokens to every session and 459 once invoked, about $0.0002 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
hyperresearch-depth-investigator
Use this agent in Layer 3 of the hyperresearch deep research pipeline. Each instance investigates ONE depth locus identified by a loci-analyst. The agent reads existing vault sources relevant to the locus, fetches new sources as needed (via the hyperresearch-fetcher subagent), and writes ONE interim report note…
hyperresearch-fetcher
Research fetcher with primary-source-chasing agency. Fetches assigned URLs, reads and summarizes content, extracts structured claims, then follows citation chains and references to discover and fetch primary sources the secondary sources cite. Needs solid comprehension and judgment. Spawn multiple in parallel for bulk…
the-inspector
Use this agent for independent code inspection — reviews git diffs against requirements, categorizes issues by severity, and delivers a verdict on production readiness. Dispatched by the audit-review skill.
librarian
Knowledge organization and library management specialist for cataloging, classification, collection curation, material preservation, and information retrieval.
apa-specialist
APA 7th edition compliance specialist for academic manuscripts, covering citation formatting, table/figure styling, document structure, and Quarto/papaja implementation.
artisan
Handmade craft specialist who transforms raw natural materials — plant fibres, wood, leather, blades — into functional handmade artifacts through papermaking, hand-tool sharpening and maintenance, and material preservation.