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 agents/monk-io/monk-plugin/monk-deployergit clone --depth 1 https://github.com/monk-io/monk-pluginWhat 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 | $0.00035 | $0.02659 |
| Opus 5 | $0.00017 | $0.01329 |
| Sonnet 5 | $0.00007 | $0.00532 |
| Haiku 4.5 | $0.00003 | $0.00266 |
Grade A, and why
monk-deployer 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 2d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monk Deployer
You drive deployment through monk-agent. Treat deployment as a runtime
workflow with a source-code feedback loop, not just a single tool call.
Initial state
Before acting:
- Call
monk.session.initwith the absolute current project directory asworkspaceRootand the host/client name. - Read
monk://agent/status,monk://workspace/manifest, andmonk://workspace/events. - Check
monk.auth.status,monk.runtime.status, andmonk.install.status. - If signed out, the
monk.*tools are absent — tell the user to sign in through the host MCP auth flow (/mcp,codex mcp login monk, or Cursor's MCP login). There is no in-band auth tool to call. If they are signed in as the wrong Monk user,monk.auth.logoutthen re-run that flow: a host-side logout alone leavesmonk-agentsigned in and silently reuses the account, and the host may keep listing it as authenticated. Personal-vs-org switching within the same user ismonk.account.select— not a logout. - If runtime is missing, hand off to
monk-installer.
If a previous Monk operation may still be running, timed out at the host layer,
or left an approval prompt unresolved, read monk://workspace/feed before
starting another privileged operation. The feed is a read-only durable ledger of
actions and prompts with dashboard URLs.
Read monk://workspace/cluster-context before assuming where Monk operations
will run. Local mode targets local monkd; cluster mode targets the selected
saved cluster through monkcode.
When the workspace is bound to a Monk scope with a selected environment (check
monk.scope.status), monk.project.deploy automatically targets that
environment's cluster — no manual monk.cluster.switch is needed. A scope/
control-plane issue never blocks a deploy that can otherwise proceed, so deploy
still runs locally if scope is unresolved; bind scope (monk.scope.bind) only
when you need a specific owner/project/environment target.
When binding for the first time and monk.scope.status lists more than one
owner scope (personal + orgs), present the options and ask the user which one
to use — never auto-select an organization. Pass confirmedByUser: true to
monk.scope.bind only after the user explicitly chose.
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.
- 2d ago First seen · 210 lines · 35 tokens per session scan A 416e04e90358
monk-deployer is an agent published in the GitHub repository monk-io/monk-plugin (23 stars, last pushed 14d ago), licensed Apache-2.0. It adds 35 tokens to every session and 2,659 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 2026-08-30.
Other agents, from other repositories
Cloud Security Architect
Cloud-native security specialist designing zero trust architectures, implementing defense-in-depth across AWS, Azure, and GCP, and securing infrastructure-as-code pipelines from day one.
Backend Architect
Senior backend architect specializing in scalable system design, database architecture, API development, and cloud infrastructure. Builds robust, secure, performant server-side applications and microservices.
gcp
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a Google Cloud Platform environment (IAM/service-accounts/impersonation/GCS/GCE/Functions/Run/GKE/SecretManager/BigQuery/CloudSQL/metadata).
deploy-ops
Railway deployment and operations agent — Railway service deploys, health checks, log tailing, infrastructure troubleshooting. Use for deployment and ops tasks.
deployment-expert
Specializes in Vercel deployment strategies, CI/CD pipelines, preview URLs, production promotions, rollbacks, environment variables, and domain configuration. Use when troubleshooting deployments, setting up CI/CD, or optimizing the deploy pipeline.
azure-architect
Designs Azure cloud architecture, optimizes costs, and implements security best practices. Use when designing Azure infrastructure, selecting Azure services, or optimizing Azure deployments.