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 skills/snowflake-labs/snowflake-ai-kit/cortex-runnpx skills add Snowflake-Labs/snowflake-ai-kit --skill cortex-rungit clone --depth 1 https://github.com/Snowflake-Labs/snowflake-ai-kitWrote 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/snowflake-ai-kit/cortex-run)<a href="https://agentmods.dev/skills/snowflake-labs/snowflake-ai-kit/cortex-run"><img src="https://agentmods.dev/badge/skills/snowflake-labs/snowflake-ai-kit/cortex-run.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 | $0.00052 | $0.01194 |
| Opus 5 | $0.00026 | $0.00597 |
| Sonnet 5 | $0.00010 | $0.00239 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade C, and why
cortex-run scanned grade C with 1 finding 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| **RW** | Data modifications, DDL | Destructive Bash (rm -rf, sudo) | How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cortex Code (Explicit Invocation)
Send a prompt directly to Cortex Code CLI, bypassing the auto-routing keyword filter. Use this when the user explicitly wants Cortex Code to handle their request.
Prerequisites
Cortex Code CLI must be installed and on PATH:
which cortex && cortex --version
If cortex is not found, load the snowflake-cortex-code:cortex-setup skill to install it. Do NOT proceed without it.
Workflow
Step 1: Check Cortex CLI
This step is mandatory. Do it first, every time.
which cortex 2>/dev/null && cortex --version
If cortex is NOT found or the command fails:
- Tell the user: "Cortex Code CLI is not installed. Setting it up now."
- Load the
snowflake-cortex-code:cortex-setupskill using the Skill tool. - Follow its instructions to install the CLI.
- STOP here — do NOT proceed to Step 2 until the CLI is installed and working.
Step 2: Extract the User Prompt
The user's message after $cortex-run is the prompt to send. If the user typed only $cortex-run with no additional text, ask what they want to do in Snowflake.
Step 3: Choose Security Envelope
Pick the envelope based on what the operation needs:
| Envelope | Use when | Blocks |
|---|---|---|
| RO | Queries, reads, exploration | Edit, Write, destructive Bash |
| RW | Data modifications, DDL | Destructive Bash (rm -rf, sudo) |
| RESEARCH | Exploration + web access | Edit, Write, destructive Bash |
| DEPLOY | Full access needed | Nothing |
Default to RW unless the request is clearly read-only.
Step 4: Execute via Cortex Code
Run the prompt through the execution script:
python "${CLAUDE_PLUGIN_ROOT}/scripts/router/execute_cortex.py" \
--prompt "USER_PROMPT_HERE" \
--envelope "RW"
For read-only queries:
python "${CLAUDE_PLUGIN_ROOT}/scripts/router/execute_cortex.py" \
--prompt "USER_PROMPT_HERE" \
--envelope "RO"
To specify a Snowflake connection:
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.
- 5d ago First seen · 146 lines · 52 tokens per session scan C 3cafe6938d7a
cortex-run is a skill published in the GitHub repository Snowflake-Labs/snowflake-ai-kit (37 stars, last pushed 23d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,194 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].
pod-init
Initialize CocoPlus project bundle in the current directory. Creates .cocoplus/ directory structure, copies all templates, initializes AGENTS.md, project.md, flow.json, and creates the initial git commit. Run this once per project before using any other CocoPlus command.
spec
Enter the Spec phase of CocoBrew. Guides the developer through structured requirements capture: goal, success criteria, constraints, personas involved, data sources, and deliverables. Writes spec.md to .cocoplus/lifecycle/ and creates a git commit.
cocoharvest
Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…
pull
Distill large context files (evaluation artifacts, schema dumps, query result sets, analysis outputs) into LLM-optimized dense form or human-readable narrative (--human). Default output is machine-dense; --human produces a prose summary for stakeholder consumption.
cocoscout
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.