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 map-explaingit 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-explain)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/map-explain"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/map-explain/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/map-explain"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/map-explain.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00026 | $0.01007 |
| Opus 5.5 | $0.00010 | $0.00403 |
| Sonnet 5.5 | $0.00005 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
map-explain 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 1mo 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$map explain <target>
Explain a specific function, capability, or schema element in domain terms using the committed coco-map.json. Answers: what it does, what depends on it, what it depends on, and how it relates to the nearest business capability.
Preconditions
.cocoplus/must be initialized.cocoplus/map/coco-map.jsonmust exist (run$mapfirst)<target>argument must be provided
Arguments
<target>(required): A function name, business capability name, or schema element name to explain. Case-insensitive matching is applied.
Step-by-Step Behavior
-
Verify initialization: Check
.cocoplus/exists. If not, output: "CocoPlus not initialized. Run$pod initfirst." and exit. -
Verify map exists: Check
.cocoplus/map/coco-map.jsonexists. If not, output:No function knowledge graph found. Run $map first to build it.and exit.
-
Read
coco-map.json: Load all structural and domain sections. -
Locate target: Search for
<target>across:- Function names in
structural.functions - Capability names in
domain.capabilities - Vocabulary terms in
domain.vocabulary - Apply case-insensitive fuzzy match (substring match if exact match not found)
- Function names in
-
If not found: Output:
No function or capability named '[target]' found in coco-map.json. Available functions: [comma-separated list] Available capabilities: [comma-separated list] Run $map to refresh the map if the project has changed.and exit.
-
Build explanation depending on target type:
For a function:
[function-name] — Cortex AI Function
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
What it does:
[domain-level description from domain.vocabulary and domain.capabilities]
Cortex API: [AI_CLASSIFY / AI_COMPLETE / etc.]
File: [file-path]
Schema: [database.schema.function-name]
Business capability:
[nearest capability from domain.capabilities, or "Not associated with a named capability"]
Dependencies (what it depends on):
Direct: [list of functions/tables this function depends on]
Transitive: [second-level dependencies if notable]
[or: "No upstream dependencies"]
Dependents (what depends on it):
Direct: [list of functions that call or depend on this one]
Transitive: [downstream functions up to 3 hops]
[or: "No downstream dependents — this is a leaf function"]
Evaluation coverage:
[Evaluation set name and baseline accuracy if available, or "No evaluation baseline — Gap detected"]
Last analyzed: [timestamp from coco-map.json meta.generated_at]
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.
- 1mo ago First seen · 138 lines · 26 tokens per session scan A 281a2e8c4a17
map-explain is a skill published in the GitHub repository Snowflake-Labs/cocoplus (724 stars, last pushed 16d ago), licensed MIT. It adds 26 tokens to every session and 1,007 once invoked, about $0.0001 per session on Opus 5.5. 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.
natural
Render the provided prompt template with Jinja context and send it to the active NPC's LLM. The rendered text becomes the user prompt; the LLM response is placed in context['output'].
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.
error-analysis
Evals-first error analysis for LLM apps: clusters real Langfuse or JSONL traces into a human-confirmed failure taxonomy with counts, then recommends binary pass/fail evals for recurring named modes. Use to learn what to measure before writing evals. Not for CI failures.
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.