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 monte-carlo-data/mc-agent-toolkit --skill onboardinggit clone --depth 1 https://github.com/monte-carlo-data/mc-agent-toolkitWrote 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/monte-carlo-data/mc-agent-toolkit/onboarding)<a href="https://agentmods.dev/skills/monte-carlo-data/mc-agent-toolkit/onboarding"><img src="https://agentmods.dev/badge/skills/monte-carlo-data/mc-agent-toolkit/onboarding/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/monte-carlo-data/mc-agent-toolkit/onboarding"><img src="https://agentmods.dev/badge/skills/monte-carlo-data/mc-agent-toolkit/onboarding.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 | $0.00000 | $0.12649 |
| Opus 5.5 | $0.00000 | $0.05060 |
| Sonnet 5.5 | $0.00000 | $0.02530 |
| Haiku 4.5 | $0.00000 | $0.01265 |
Grade A, and why
monte-carlo-onboarding 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 3d 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 — 747 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monte Carlo Onboarding
Walk a customer from "connect <warehouse or BI tool> to Monte Carlo" to working connections,
one or several, using the Monte Carlo MCP tools for deployments, credentials, warehouses, BI
containers and connections. Start by showing what already exists and what can be added, then
resolve only the missing customer decisions, and reuse or provision the deployment before
creating a connection. A request to connect Snowflake does not imply that the customer knows
which deployment or collection agent they need.
A warehouse connection goes on a warehouse. A Tableau, Looker or Power BI connection goes on a
BI container instead: the BI tool's counterpart of a warehouse, with a type (tableau,
looker or power-bi) and a deployment. The steps are the same; Step 3 picks the parent.
A custom connector is a connection type a customer's collection agent registered, or one whose data the customer pushes. Its type decides the parent and the deployment; Custom connectors, after Step 5, adapts Steps 1 to 5 for it.
Tools and supporting references
Use the configured Monte Carlo MCP connection for the intended account. If multiple connections are available, verify the account before choosing one. Tool names below identify operations; match them to the tools and schemas exposed by the current environment.
Read the supporting references with the environment's available file or resource capability:
- API references in
reference/api/<tag>.md: per-tag arguments, responses and failure modes.
- Deployment guide: prerequisites, networking and handoffs.
- Output modes: Terraform, SDK and CLI examples.
- Connection inputs: the inputs each deployment, credential path and connection type requires, and where each value must come from.
- Troubleshooting: a connection that worked and now fails; the order of checks and what each validation result means.
What ships with it
18 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.
- README.md 8.5 KB
- reference/api/bi-containers.md 9.6 KB
- reference/api/collection-agents.md 40 KB
- reference/api/collection-data-stores.md 19 KB
- reference/api/connection-types.md 4.4 KB
- reference/api/connections.md 24 KB
- reference/api/credentials.md 153 KB
- reference/api/custom-connector-types.md 4.8 KB
- reference/api/deployments.md 12 KB
- reference/api/etl-containers.md 11 KB
- reference/api/integration-keys.md 6.9 KB
- reference/api/users.md 2.2 KB
- reference/api/validations.md 3.2 KB
- reference/api/warehouses.md 10 KB
- reference/connection-inputs.md 23 KB
- reference/deployment-guide.md 8.2 KB
- reference/output-modes.md 45 KB
- reference/troubleshooting.md 6.2 KB
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.
- 3d ago Changed · +151 lines 12b6bbe5f0e1
- 10d ago Changed · +61 lines 1f8c384cf475
- 15d ago Changed · +13 lines caabb377f7d5
- 16d ago Changed · +69 lines · -59 tokens per session 8103bc58fc3d
- 17d ago Changed · +8 lines 0adbecce0e9c
- 18d ago Changed · +28 lines 6eab257b8638
- 21d ago Changed · +47 lines 38e48f6e97d2
- 22d ago First seen · 370 lines · 59 tokens per session scan A bc62326b59ec
monte-carlo-onboarding is a skill published in the GitHub repository monte-carlo-data/mc-agent-toolkit (93 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 12,649 tokens. 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 2026-09-25.
Other skills, from other repositories
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
cqrs-implementation
Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.
projection-patterns
Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.
release-db-config-sync
Compute the remote DB migration + Nacos config diff before a test release — apc release db-config-sync really spawns sync-test-migrations.ts --dry-run (never a stub) and diffs Nacos key dumps, stopping at the write boundary. green(0) no diff · staged(3) pending migrations/missing keys await approval · blocked(1) real…
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.