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/jamestelfer/sandy/sandy-mcpnpx skills add jamestelfer/sandy --skill sandy-mcpgit clone --depth 1 https://github.com/jamestelfer/sandyWrote 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/jamestelfer/sandy/sandy-mcp)<a href="https://agentmods.dev/skills/jamestelfer/sandy/sandy-mcp"><img src="https://agentmods.dev/badge/skills/jamestelfer/sandy/sandy-mcp.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 | $0.00056 | $0.00173 |
| Opus 5 | $0.00028 | $0.00086 |
| Sonnet 5 | $0.00011 | $0.00035 |
| Haiku 4.5 | $0.00006 | $0.00017 |
Grade A, and why
sandy-mcp 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 6d 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.
What it actually says
Sandy (MCP)
This plugin registers the Sandy MCP server. Sandy's real instructions live in its prime tool,
not here.
First action
Call the MCP prime tool:
prime()
Read its complete output before doing anything else. It documents the available sandy_* tools,
the IMDS credential flow, and the sandy://skills/mcp/resources/... links you need for
script-authoring guidance.
Follow every resource link prime gives you before writing or running a script.
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.
- 6d ago First seen · 24 lines · 56 tokens per session scan A 919f52d2e74c
sandy-mcp is a skill published in the GitHub repository jamestelfer/sandy (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 173 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
aws-cdk
AWS CDK infrastructure development in TypeScript. Use when creating stacks, constructs, L2/L3 patterns, CDK testing, synth/deploy pipelines or organizing IaC code.
aws-serverless
Building production-ready serverless applications on AWS. Use when working with Lambda, API Gateway, SQS, SNS, DynamoDB Streams, SAM/CDK deployment or optimizing cold starts.
aws-terraform
AWS infrastructure with Terraform. Use when creating modules, managing remote state, writing tftest.hcl tests, refactoring IaC or following HashiCorp style guide.
aws-architecture
AWS architecture decisions, serverless patterns, event-driven design, service boundaries and Well-Architected Framework. Use when designing system architecture or making infrastructure tradeoffs.
aws-lambda-python
AWS Lambda development with Python. Use when writing Lambda handlers, packaging with layers, using boto3/Powertools, structured logging or optimizing Python Lambda performance.
aws-security
AWS security implementation. Use when configuring IAM policies, managing secrets, setting up encryption, securing networking, hardening services or auditing configurations.