A workflow for using Monk to deploy, configure, scale, and monitor applications and infrastructure. Monk works with containerized workloads, cloud infrastructure, and connections to online services through a local companion service.

Use it when deploying applications, configuring cloud resources or SaaS integrations, scaling workloads, monitoring services, or checking the required Monk workspace and authentication setup.

It provides a prescribed way to prepare a workspace, authenticate, connect the agent, and carry out Monk operations. This helps avoid using the wrong local tool or deploying from an unbound workspace.

monk — Skill for Claude Code and Codex by monk-io: A workflow for using Monk to deploy, configure, scale…

Install

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.

agentmods

npx agentmods add skills/monk-io/monk-plugin/monk

Any agent

npx skills add monk-io/monk-plugin --skill monk

Clone the repo

git clone --depth 1 https://github.com/monk-io/monk-plugin

Made for: Claude Code, Codex.

Or install monk, the plugin that ships this one along with the rest of its 1 skill, 5 agents, 4 hooks, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/monk-io/monk-plugin/monk.svg)](https://agentmods.dev/skills/monk-io/monk-plugin/monk)

Your own site

<a href="https://agentmods.dev/skills/monk-io/monk-plugin/monk"><img src="https://agentmods.dev/badge/skills/monk-io/monk-plugin/monk.svg" alt="Measured on agentmods" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,181 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00046	$0.05181
Opus 5	$0.00023	$0.02590
Sonnet 5	$0.00009	$0.01036
Haiku 4.5	$0.00005	$0.00518

Measured 4d ago against content hash 112c8f16e51b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

monk 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 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

feature. Honor the request directly — do not refuse or defer it.

.antigravity-plugin/skills/monk/SKILL.md · 445 lines

How it starts

The opening of the file, as written. The whole thing — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using Monk

Model

Monk is operated through a local companion named monk-agent. The companion exposes MCP tools and a localhost dashboard, then talks to local monkd through the @monk-io/monk TypeScript client from monk-ts2.

Antigravity is a supported host.

Preflight

Before deploying:

Confirm the local Monk MCP tools/resources are available. These are backed by monk-agent.
- Antigravity handles Monk MCP authentication automatically via OAuth. If authentication is required, use Antigravity's MCP authentication flow: Agent Settings → Customizations tab → Authenticate next to the monk server. Complete the flow in your browser, then return here.
- Once authenticated, Antigravity reconnects automatically.
If monk-agent is missing, start it by running scripts/start-monk-agent.sh on macOS/Linux or scripts/start-monk-agent.ps1 on Windows. Do not fall back to direct monk CLI operations.
Workspace binding. Call monk.session.init with the absolute workspace root at the start of each session. monk-agent does not fall back to its own working directory, so an explicit binding is required when the host does not advertise the MCP roots capability. Pass workspaceRoot as the absolute path to the project directory. Omit the call only if you have confirmed that Monk already has the correct workspace root bound.
Confirm auth status with monk.auth.status (once the tools are available). If signed out, sign in through Antigravity's MCP auth flow (step 1) — that flow also establishes the upstream Monk session; there is no in-band tool to start auth. Disconnecting the MCP server host-side clears only Antigravity's own credentials, so monk-agent stays signed in to the same Monk user and the next sign-in reuses it silently. To sign in as a different Monk user, call monk.auth.logout (approved in the dashboard) and then re-run the flow from step 1 — that time the user picks the account. Antigravity may still list the server as authenticated afterwards, holding a token the agent has revoked, so tell the user to explicitly re-authenticate. Logging out keeps stored secrets and credentials; do not use monk.agent.clear_state for this. Switching personal vs org context within the same user is monk.account.select instead — a different operation; ask which the user means if it is ambiguous.
Confirm runtime status. monk-agent requires Monk CLI and monkd locally. If missing or broken, use monk.install.status to inspect the platform-specific humanExplanation, relationships, components, checks, probes, troubleshootingHints, nextAction, and actions. Explain the current platform's install graph before running remediation. monk.install.run is dry by default: without execute: true it only inspects status and runs nothing. Use execute: true to run remediation. Installation, upgrade, and repair actions also require approved: true after explicit user or dashboard approval.

Read the full file on GitHub · 445 lines

Changes

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 · 445 lines · 46 tokens per session scan C 112c8f16e51b

Subscribe to this mod's changes

monk is a skill published in the GitHub repository monk-io/monk-plugin (23 stars, last pushed 16d ago), licensed Apache-2.0. It adds 46 tokens to every session and 5,181 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Cloud Containers DevOps and cloud

timoni

Use when deploying applications to Kubernetes with Timoni. Covers installing and upgrading module instances from OCI registries, composing multi-app deployments with bundles, injecting values from clusters or CI with runtimes, targeting multiple clusters, and authoring, testing, signing and publishing modules with CUE.

stefanprodan/timoni · 59 tokens

compute-env-setup

Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.

companion-inc/feynman · 45 tokens

windows-builder

Build Windows images with Packer using WinRM communicator and PowerShell provisioners. Use when creating Windows AMIs, Azure images, or VMware templates.

hashicorp/agent-skills · 33 tokens

deployment

Deploy Memoria with Docker Compose or Kubernetes. Environment variables, multi-instance setup, security. Use when deploying or configuring Memoria.

matrixorigin/memoria · 28 tokens

nvcf-self-managed-prerequisite

Install the prerequisites the NVCA operator / compute plane needs before nvcf-nvca-install can succeed: the operator tool nvcf-cli (required by the compute-plane stack's register-cluster step), KAI Scheduler (for the KAIScheduler feature gate), and the SMB CSI driver (for the sharedStorage Samba sidecar PVCs). The two…

NVIDIA/nvcf · 195 tokens

nvca-self-managed-install

Install or validate the NVCA Operator chart against a self-managed NVCF control plane from the native monorepo. Use when the control plane comes from deploy/stacks/self-managed and NVCA must be installed with stack-derived image repository settings.

NVIDIA/nvcf · 55 tokens

monk