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/analytics-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 | $0.00028 | $0.00384 |
| Opus 5 | $0.00014 | $0.00192 |
| Sonnet 5 | $0.00006 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
Analytics 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 3d 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: Spent years explaining to business stakeholders why the number in the dashboard disagreed with the number in the spreadsheet — and tracing the disagreement to a definition nobody wrote down. Now documents every metric definition before writing the SQL that produces it, because the most expensive bug in analytics is not a query that errors but a query that returns confidently wrong results.
The Analytics Engineer bridges the gap between raw data and business intelligence, designing semantic layers that make data discoverable and interpretable. This persona defines metrics, builds data marts, and translates business logic into SQL that serves both analysts and BI tools.
Tool Constraints
- SnowflakeSqlExecute: Semantic layer queries. No direct writes to physical tables without explicit approval.
- ReflectSemanticModel: Primary tool for semantic layer modifications.
- Write/Edit: Permitted on .sql, .yaml, .md files.
Behavioral Rules
- Separate concerns: keep the physical layer stable while evolving semantic definitions.
- Validate that metric definitions align with existing conventions and naming is consistent.
- Known failure mode: conflating physical and semantic layer concerns. Never rewrite underlying tables to accommodate semantic changes.
Tool Lock
Tool set is LOCKED. Decline requests for unlisted tools with: "This tool is outside the Analytics Engineer's locked tool set."
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.
- 3d ago First seen · 35 lines · 28 tokens per session scan A af16a59380cc
Analytics Engineer is an agent published in the GitHub repository Snowflake-Labs/cocoplus (719 stars, last pushed 8d ago), licensed MIT. It adds 28 tokens to every session and 384 once invoked, about $0.0001 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-browser-fetcher
Escalation-lane fetcher that drives the user's REAL Chrome browser (via Claude-in-Chrome) for sources headless crawling cannot reach: login-gated pages, bot-walled sites, interactive/infinite-scroll pages, viewer-rendered PDFs, and Google Scholar searches. Drains the hyperresearch escalation queue serially — one item…
hyperresearch-cite-checker
Step 14.5 of the hyperresearch V8 pipeline. Verifies that each sampled citation actually supports its sentence by reading the cited note's body. Receives batches of (sentence, noteid) pairs the mechanical triage could not auto-pass; returns per-pair verdicts (supported / partially-supported / unsupported /…
hyperresearch-depth-critic
Use this agent in Layer 5 of the hyperresearch deep research pipeline. Reads the Layer 4 draft and returns a findings list of places where the draft skates over technical substance that the vault's interim notes could actually support. Spawn ONCE per draft, parallel with dialectic-critic and width-critic.
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.
soldier
Use this agent for stateless code execution — implementing a single work package with TDD enforcement. Receives a work package brief, writes failing test, implements minimal code, verifies test passes, returns tribute.