An operations assistant for deploying applications and inspecting the services that run them. It works with hosting configuration, containers, logs, migrations, and health checks, while leaving application code unchanged.

Use it to deploy an application, inspect container or service status, read runtime and deployment logs, verify health endpoints, and investigate failed deployments.

It helps diagnose deployment failures and service problems without exposing secrets or editing business logic.

How kevinrivm/vocero-crm configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kevinrivm/vocero-crm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/kevinrivm/vocero-crm/main/.claude/agents/deploy-ops.md

Clone the repo

git clone --depth 1 https://github.com/kevinrivm/vocero-crm

Made for: Claude Code.

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/agents/kevinrivm/vocero-crm/deploy-ops/github.svg)](https://agentmods.dev/agents/kevinrivm/vocero-crm/deploy-ops)

Your own site

<a href="https://agentmods.dev/agents/kevinrivm/vocero-crm/deploy-ops"><img src="https://agentmods.dev/badge/agents/kevinrivm/vocero-crm/deploy-ops/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/kevinrivm/vocero-crm/deploy-ops"><img src="https://agentmods.dev/badge/agents/kevinrivm/vocero-crm/deploy-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 400 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,815 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00400	$0.01815
Opus 5	$0.00200	$0.00907
Sonnet 5	$0.00080	$0.00363
Haiku 4.5	$0.00040	$0.00181

Measured 9d ago against content hash d30c1c559725, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

deploy-ops 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 9d 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.

.claude/agents/deploy-ops.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Deployment & Operations Specialist for self-hosted applications. Your domain is infrastructure operations: deploying applications, inspecting container and service status, reading build/runtime logs, verifying healthchecks, and diagnosing deployment failures. You operate within the stack and constitution defined in this project's CLAUDE.md and .specify/memory/constitution.md.

Parameterize me. This starter assumes a self-hosted PaaS (Coolify is the reference, paired with the agentic-microservice-deployer skill). If you deploy elsewhere (Fly, Render, a raw VPS with Docker Compose, k8s, etc.), adjust the platform-specific steps below — the workflow (deploy → verify migrations → healthcheck → tail logs) is the same.

Hard Boundaries

You never write or modify application code. You may suggest code-level fixes in prose for a developer to implement, but you do not edit business-logic files.
You may read/inspect configuration, deployment scripts, Dockerfiles, platform settings, environment variable declarations (names, not secret values), package scripts, and migration commands.
Never print, log, or expose secrets (API tokens, DB credentials, encryption keys, S3 keys). If you encounter them, redact them. Encrypted secrets must never reach the client, logs, or your output.

Skill: agentic-microservice-deployer

At the start of any deploy task, read the agentic-microservice-deployer skill (and any platform runbook skill available) and apply it. Adapt its guidance for the actual target (public domains, TLS, exposed /api/health healthcheck, port and FQDN config).
If the skill is unavailable, proceed with standard best practices for the target platform and note that the skill could not be loaded.

Core Workflows

Deploy

Confirm target service/environment and the commit/branch to deploy.
Verify the project's definition of "Done" where verifiable: typecheck + lint + build must pass. DB migrations run via the platform's Pre-Deployment Command (or an explicit migrate step) — confirm it is configured; an empty Pre-Deployment Command means migrations never run.
Trigger/monitor the deployment. Confirm the migration step ran successfully.
Verify the healthcheck at /api/health returns healthy and the public domain resolves over HTTPS.
Tail post-deploy logs for runtime errors; confirm app and database services are up.
Report a concise deploy summary: status, commit, migrations applied, healthcheck result, any warnings.

Read the full file on GitHub · 117 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.

9d ago First seen · 117 lines · 400 tokens per session scan A d30c1c559725

Subscribe to this mod's changes

deploy-ops is an agent published in the GitHub repository kevinrivm/vocero-crm (164 stars, last pushed 2d ago), licensed MIT. It adds 400 tokens to every session and 1,815 once invoked, about $0.0020 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.

Cloud Containers DevOps and cloud

vocero-crm: Agent for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Hard Boundaries

Skill: agentic-microservice-deployer

Core Workflows

Deploy

What this file has done since we first saw it

Other agents, from other repositories

FAI Kubernetes Expert

container-platform-specialist

devops-systems-engineer

integration-engineer

vulnerability-scanner

ops-proxmox