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/mcpnpx skills add jamestelfer/sandy --skill 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/mcp)<a href="https://agentmods.dev/skills/jamestelfer/sandy/mcp"><img src="https://agentmods.dev/badge/skills/jamestelfer/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 | $0.00045 | $0.01802 |
| Opus 5 | $0.00023 | $0.00901 |
| Sonnet 5 | $0.00009 | $0.00360 |
| Haiku 4.5 | $0.00005 | $0.00180 |
Grade A, and why
sandy 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 4d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sandy
Sandy executes TypeScript scripts in disposable sandboxed environments (Shuru microVMs or Docker containers) with AWS credentials from IMDS.
Sandy now uses explicit sessions for all MCP operations. There is no implicit active session.
Setup
Read the scripting guide before writing scripts:
resource: sandy://skills/mcp/resources/scripting-guide.md
This guide defines runtime constraints, available AWS SDK packages, and the required async generator pattern.
IMDS port
AWS credentials are provided by an IMDS server on the host. Use imds-broker to start one:
imds-broker: start_server(profile="myaccount-ReadOnly", region="us-west-2") → "http://localhost:9001"
Pass the port number (for example 9001) to sandy_run and sandy_check(action: "connect").
MCP tools
sandy_create_session
Create a session and return where scripts must be written.
sandy_create_session()
Returns: { sessionName, scriptsPath }
sandy_resume_session
Resume an existing session and return its scripts path.
sandy_resume_session(sessionName: "happy-fox-trail")
Returns: { sessionName, scriptsPath }
sandy_image
Create or delete the Sandy sandbox image.
sandy_image(action: "create")
sandy_image(action: "delete")
sandy_check
Run a health check. Sandy creates and deletes an ephemeral session for each check; no session parameter is accepted.
sandy_check(action: "baseline")
sandy_check(action: "connect", imdsPort: 9001)
sandy_check(action: "connect", imdsPort: 9001, region: "ap-southeast-2")
Returns: { exitCode, output }
sandy_run
Run a TypeScript script from the session scripts/ directory.
sandy_run(
session: "happy-fox-trail",
script: "inventory.ts",
imdsPort: 9001,
region: "us-west-2", // optional, default us-west-2
args: ["arg1", "arg2"] // optional
)
For MCP clients without filesystem access, provide inline content. Sandy writes it to scripts/<script> before execution.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 202 lines · 45 tokens per session scan A 5f1c1540f8d0
sandy is a skill published in the GitHub repository jamestelfer/sandy (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,802 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 2026-08-31.
Other skills, from other repositories
aws-lambda-typescript
AWS Lambda development with TypeScript. Use when writing Lambda handlers, bundling with esbuild, using AWS SDK v3/Powertools, strict typing or optimizing Node.js Lambda performance.
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.
typescript-runtime
TypeScript toolchain configuration and best practices. Use when setting up tsconfig, ESLint, Prettier, Vitest, bundling, type patterns or TypeScript project standards.
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
semantic-compression
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…