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 leangit 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/lean)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/lean"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/lean/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/lean"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/lean.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 | $0.00041 | $0.01253 |
| Opus 5.5 | $0.00016 | $0.00501 |
| Sonnet 5.5 | $0.00008 | $0.00251 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
cocolean 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cocolean — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objective
You are executing CocoLean — the minimum viable Cortex surface discipline. Your task depends on how this skill was invoked:
$lean/$lean full— activate full mode (all three CocoLean modes), run the pre-build decision ladder$lean lite— switch to lite mode (ladder only), run the pre-build decision ladder$lean ultra— switch to ultra mode (full + enforcement), run the pre-build decision ladder$leanwith no prior context — treat as$lean full
Before proceeding, verify that .cocoplus/ exists. If not, output: "CocoPlus is not initialized. Run $pod init first." Then stop.
Step 1 — Set Intensity Level
Parse the invocation:
| Command | Mode | Write to .cocoplus/modes/lean.mode |
|---|---|---|
$lean lite |
lite |
lite |
$lean full |
full |
full |
$lean ultra |
ultra |
ultra |
$lean |
full (default) |
full |
Write the mode string to .cocoplus/modes/lean.mode. Confirm: "CocoLean mode set to [mode]."
If .cocoplus/modes/lean.mode already exists, read its current value and note the change: "CocoLean mode changed from [previous] to [new]."
Step 2 — Run the Pre-Build Decision Ladder
Surface the six-rung Cortex-adapted decision ladder. Present it as a checklist the developer must work through before writing any new Cortex AI function, pipeline stage, or subagent:
CocoLean Decision Ladder — work top to bottom, stop at the first YES:
[ ] Rung 1: Can a deterministic rule, SQL expression, lookup table, or threshold accomplish this without AI inference?
[ ] Rung 2: Does a Snowflake native built-in handle it? (FLATTEN, MATCH_RECOGNIZE, window functions, conditional expressions, SEARCH, OBJECT_CONSTRUCT…)
[ ] Rung 3: Does an existing UDF, stored procedure, or Cortex function in this project already solve this?
[ ] Rung 4: Would a single AI_COMPLETE call with a well-scoped prompt be sufficient?
[ ] Rung 5: Can the minimum working function be written in under ten lines? (Write the minimum version first — complexity is earned, not assumed.)
[ ] Rung 6: A full Cortex function or multi-stage pipeline is justified. Proceed to build.
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 · 102 lines · 41 tokens per session scan A 0f4540257ab8
cocolean is a skill published in the GitHub repository Snowflake-Labs/cocoplus (726 stars, last pushed 23d ago), licensed MIT. It adds 41 tokens to every session and 1,253 once invoked, about $0.0002 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'].
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
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.