Agent Claude Code
Models semantic layers, defines business metrics, designs data marts, and encodes business logic in SQL. Invoke with $ae.
not rated 724 11d ago A 28 tokens
original MIT
BI Analyst
02Agent Claude Code
Designs dashboards, builds Snowsight reports, creates visualizations, and translates business questions into BI artifacts. Invoke with $bi.
not rated 724 11d ago A 30 tokens
original MIT
Agent Claude Code
Reviews data strategy, evaluates architecture decisions, assesses risk and compliance posture, and provides executive-level perspective. Invoke with $cdo.
not rated 724 11d ago A 30 tokens
original MIT
CocoBloom
04Agent Claude Code
Working-backwards pre-commitment facilitator. Runs the $bloom dialogue and writes the lifecycle bloom artifact.
not rated 724 11d ago A 26 tokens
original MIT
CocoCupper
05Agent Claude Code
Post-execution intelligence analyst. Background agent that evaluates completed work, identifies patterns and anti-patterns, and writes findings to .cocoplus/grove/cupper-findings.md. Triggered automatically on session end.
not rated 724 11d ago A 48 tokens
original MIT
CocoKlatch
06Agent Claude Code
Roundtable orchestrator. Prepares a topic brief, coordinates independent participant outputs, and synthesizes decision-ready findings.
not rated 724 11d ago A 28 tokens
original MIT
CocoPull
07Agent Claude Code
Lossless context distillation agent. Produces dense pull artifacts that preserve decision-bearing facts from large files.
not rated 724 11d ago A 25 tokens
original MIT
CocoScout
08Agent Claude Code
Background context ranker. Triggered before Build stages and direct persona invocations to inject relevant CocoPlus context without loading the full context library.
not rated 724 11d ago A 32 tokens
original MIT
CocoWatch
09Agent Claude Code
Non-blocking developer engagement observer. Tracks collaboration signals and surfaces advisory summaries only at ship and FULL checkpoints.
not rated 724 11d ago A 25 tokens
original MIT
CocoBrew
10Agent Claude Code
CocoBrew lifecycle coordinator. Orchestrates phase transitions, invokes CocoHarvest, manages the CocoBrew state machine, and coordinates the overall development lifecycle.
not rated 724 11d ago A 37 tokens
original MIT
Data Analyst
11Agent Claude Code
Performs exploratory analysis, builds ad-hoc queries, interprets business metrics, and produces analytical reports. Invoke with $da.
not rated 724 11d ago A 29 tokens
original MIT
Agent Claude Code
Designs schemas, builds SQL pipelines, writes dbt models and stored procedures, and optimizes data transformations. Invoke with $de.
not rated 724 11d ago A 30 tokens
original MIT
Agent Claude Code
Defines data product requirements, manages roadmap, writes PRDs for data features, and ensures data products meet stakeholder needs. Invoke with $dpm.
not rated 724 11d ago A 33 tokens
original MIT
Agent Claude Code
Develops ML models, engineers features, works with Snowpark notebooks and Cortex ML functions, and conducts statistical analysis. Invoke with $ds.
not rated 724 11d ago A 31 tokens
original MIT
Data Steward
15Agent Claude Code
Manages data governance, enforces data quality standards, defines data lineage, and ensures compliance with data policies. Invoke with $dst.
not rated 724 11d ago A 30 tokens
original MIT
Agent Claude Code
Background Snowflake environment scanner. Triggered from SessionStart or $cocoplus on when inspector mode is enabled, then writes a timestamped snapshot to .cocoplus/snapshots/.
not rated 724 11d ago A 41 tokens
original MIT
Agent Claude Code
Background SQL reviewer. Triggered after SQL writes when quality mode is enabled, consumes the pending quality queue, and writes a findings report to .cocoplus/.
not rated 724 11d ago A 35 tokens
original MIT
Agent Claude Code
SecondEye adversarial reviewer. Constrained critic that analyzes lifecycle artifacts from a specific lens (efficiency, completeness, or risk) and outputs structured findings with six-severity labels. Invoked by $secondeye in parallel at three model tiers.
not rated 724 11d ago A 55 tokens
original MIT
cocobehavior
19Skill Claude Code
Cortex-specific behavioral guidelines — always-on inner constraint layer for all CocoPlus personas.
not rated 724
changed 11d ago A SkillSpector: pass 22 tokens
original MIT
cocoscout
20Skill Claude Code
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
not rated 724 11d ago A SkillSpector: pass 59 tokens
original MIT
cocowatch
21Skill Claude Code
Developer engagement observer — non-blocking, always-on observational layer that tracks Delegation Intensity, Review Depth, and Engagement Zone throughout a session. Summary surfaced at $ship and FULL checkpoints.
not rated 724
changed 11d ago A SkillSpector: pass 43 tokens
original MIT
Skill Claude CodeCodex
Launch CocoConsole, the CocoPlus 2.0 read-only local browser control plane. Use $cocoplus console, $cocoplus console status, or $cocoplus console stop.
not rated 724 11d ago A 45 tokens
original MIT
cocoplus-off
23Skill Claude CodeCodex
Deactivate Full Assist Mode — removes all CocoPlus feature flags. Data files (memory, meter history, grove patterns) are preserved. Idempotent.
not rated 724 11d ago A 35 tokens
original MIT
cocoplus-on
24Skill Claude CodeCodex
Activate Full Assist Mode — enables all CocoPlus features simultaneously: Memory Engine, Environment Inspector, Safety Gate (normal), Code Quality Advisor, Context Mode, and CocoMeter. Also triggers a background environment scan. Idempotent.
not rated 724 11d ago A 50 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: