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 skills add Snowflake-Labs/cocoplus --skill mapgit clone --depth 1 https://github.com/Snowflake-Labs/cocoplusWrote 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.
[](https://agentmods.dev/skills/snowflake-labs/cocoplus/map)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/map"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/map.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.01912 |
| Opus 5 | $0.00021 | $0.00956 |
| Sonnet 5 | $0.00008 | $0.00382 |
| Haiku 4.5 | $0.00004 | $0.00191 |
Grade A, and why
map 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$map
Build and commit a knowledge graph of all Cortex AI functions in the project. Produces coco-map.json with structural dependency data and a domain intent map.
Flags
| Flag | Effect |
|---|---|
| (none) | Build full map with transitive reduction applied (default) |
--reduce |
Explicit: apply transitive reduction (same as default) |
--reduce off |
Skip transitive reduction — store full transitive closure in coco-map.json |
Preconditions
.cocoplus/must be initialized- At least 2 Cortex AI functions must exist in the project (SQL UDFs using AI_COMPLETE, AI_CLASSIFY, AI_EXTRACT, etc., or Cortex Search configurations, or Semantic Model definitions)
- CocoHarvest must be available for parallel agent coordination
Step-by-Step Behavior
-
Verify initialization: Check
.cocoplus/exists. If not, output: "CocoPlus not initialized. Run$pod initfirst." and exit. -
Count Cortex AI functions: Scan project SQL files and configuration for functions using:
AI_COMPLETE,AI_CLASSIFY,AI_EXTRACT,AI_FILTER,AI_SENTIMENT,AI_TRANSLATE,AI_EMBED,AI_SIMILARITY,AI_REDACT,AI_PARSE_DOCUMENT,AI_TRANSCRIBE,AI_AGG,AI_COUNT_TOKENS, Cortex Search service definitions, and Semantic Model files. If fewer than 2 found, output:CocoMap requires at least 2 Cortex AI functions. Only [N] found. Add more Cortex AI functions before running $map.and exit.
-
Create map directories:
.cocoplus/map/intermediate/(if not present).cocoplus/map/archive/(if not present)
-
Archive previous map: If
.cocoplus/map/coco-map.jsonalready exists, copy it to.cocoplus/map/archive/[timestamp]-coco-map.jsonbefore overwriting. This is gitignored — the archive is for debugging, not version history. -
Spawn 5 analysis agents in parallel (each writes intermediate results to
.cocoplus/map/intermediate/without returning to orchestrator context):Agent 1 — Function Scanner:
- Discovers all Cortex AI functions: SQL UDFs using AI_* functions, Cortex Search configurations, Semantic Model definitions
- Extracts: function name, file path, function signature, Cortex API used, schema/database location
- Output:
.cocoplus/map/intermediate/function-scanner-results.json
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 · 166 lines · 42 tokens per session scan A dba749ae9d83
map is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 1,912 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 2026-09-03.
Other skills, from other repositories
prompt-engineering
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, designing production prompt templates, or building AI-powered features.
rag-retrieval
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.
transformer-attention
Use when reasoning about Transformer self-attention, multi-head attention, positional encoding, masked decoder attention, or why attention replaced recurrence/convolutions in sequence models; not for generic NLP or unrelated attention topics.
testing-llm
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.
golden-dataset
Golden dataset lifecycle patterns for curation, versioning, quality validation, and CI integration. Use when building evaluation datasets, managing dataset versions, validating quality scores, or integrating golden tests into pipelines.
deepeval
Use when discussing or working with DeepEval (the python AI evaluation framework).