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 commands/gprot42/grok-mcp-cloudrun/deploygit clone --depth 1 https://github.com/gprot42/grok-mcp-cloudrunWrote 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/commands/gprot42/grok-mcp-cloudrun/deploy)<a href="https://agentmods.dev/commands/gprot42/grok-mcp-cloudrun/deploy"><img src="https://agentmods.dev/badge/commands/gprot42/grok-mcp-cloudrun/deploy.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 | $0.00017 | $0.00536 |
| Opus 5 | $0.00009 | $0.00268 |
| Sonnet 5 | $0.00003 | $0.00107 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
deploy 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy to Cloud Run
Deploy the current project folder to Google Cloud Run.
Usage
/deploy [service-name]
If no service name is given, use DEFAULT_SERVICE_NAME from the environment, or
the basename of the current working directory.
Instructions
You are a Cloud Run deployment assistant. Deploy the user's project using the Cloud Run MCP server.
Step 1: Prerequisites
Before deploying, verify:
GOOGLE_CLOUD_PROJECTis set (orgcloud config get-value projectreturns a project)- Application Default Credentials exist
(
gcloud auth application-default loginif missing) - The current directory contains deployable source (e.g.
Dockerfile,package.json, or supported runtime files)
If prerequisites fail, tell the user exactly what to run — do not attempt deploy.
Step 2: Resolve service name
Service name priority:
- Argument from
/deploy <name>if provided DEFAULT_SERVICE_NAMEenvironment variable- Basename of the current working directory (e.g.
my-app)
Step 3: Deploy via MCP
Call the MCP tool cloud-run__deploy-local-folder with:
- The current working directory as the source folder
- The resolved service name
- Project:
GOOGLE_CLOUD_PROJECT(default from env) - Region:
GOOGLE_CLOUD_REGIONorus-central1
Use search_tool to find the tool if needed, then use_tool with the
fully-qualified name cloud-run__deploy-local-folder.
Step 4: Report result
On success, return:
- Deployed service name
- Public HTTPS URL
- Project and region used
On failure, explain the error and suggest fixes (auth, IAM, missing Dockerfile, billing).
Examples
/deploy
/deploy hello-test
/deploy my-api --region us-west1
Error handling
| Error | Fix |
|---|---|
| ADC not configured | gcloud auth application-default login |
| Permission denied | Ensure roles/run.admin or run.developer + iam.serviceAccountUser |
| No deployable source | Add a Dockerfile or supported build config |
| Project not set | export GOOGLE_CLOUD_PROJECT=your-project-id |
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 First seen · 87 lines · 17 tokens per session scan A 00bca1592c36
deploy is a command published in the GitHub repository gprot42/grok-mcp-cloudrun (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 536 once invoked, about $0.0001 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 commands, from other repositories
deploy
Build, test, deploy with staged rollout.
deploy
Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.
cf-scaffold-project
Scaffold a Cloudflare project — Worker, Pages, or Worker+D1+R2 starter — with Wrangler config, Terraform skeleton, and GitHub Actions deploy using scoped API tokens.
overview
Unified cost dashboard combining state, plan, actual costs, projected costs, drift, and recommendations.
scan
Scan AWS account for cost optimization.
finops-feedback
Step 5 (Feedback Loop & Celebration) — measure realized against projected savings, compute a labelled Cloud Entropy proxy, close the opportunity, and emit at least one new idea or policy update so the loop actually closes. Applies the double-loop gate. Mutates on the closure path.