deploy-to-staging

deploy-to-staging is an agent for Claude Code from lando-labs/cami. It costs 83 tokens per session (2,432 once invoked), scanned A, original, MIT.

A deployment workflow for sending an application to a staging or QA environment, then checking it with tests and smoke tests. Staging is a pre-release environment; smoke tests are short checks that confirm the deployment works.

In plain words
What is it for?
Building applications, running tests, creating and publishing Docker images, deploying to Kubernetes staging namespaces, and running post-deployment checks.
Why use it?
It adds ordered checks around builds, containers, deployment, and verification so failed steps are caught early.

Agent for Claude Code

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 agents/lando-labs/cami/deploy-to-staging
Clone the repo
git clone --depth 1 https://github.com/lando-labs/cami

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.

agentmods badge for deploy-to-staging

README.md
[![agentmods](https://agentmods.dev/badge/agents/lando-labs/cami/deploy-to-staging.svg)](https://agentmods.dev/agents/lando-labs/cami/deploy-to-staging)
Your own site
<a href="https://agentmods.dev/agents/lando-labs/cami/deploy-to-staging"><img src="https://agentmods.dev/badge/agents/lando-labs/cami/deploy-to-staging.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,432 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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.

ModelPer sessionOnce invoked
Fable 5 $0.00083 $0.02432
Opus 5 $0.00042 $0.01216
Sonnet 5 $0.00017 $0.00486
Haiku 4.5 $0.00008 $0.00243

Measured 3d ago against content hash cfcd57eceb93, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deploy-to-staging scanned grade A 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -f https://<environment>.<domain>/health
.claude/agents/deploy-to-staging.md · 366 lines

How it starts

The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Staging Deployment Specialist, a disciplined workflow executor focused on reliable, repeatable deployments to staging and QA environments. You follow a strict sequence of validated steps, ensuring each gate passes before proceeding to the next.

Core Philosophy: The Chain of Verification

Every deployment is only as strong as its weakest link. You execute each step with precision, verify its success explicitly, and halt immediately when something fails. You never skip steps, never assume success, and never proceed without confirmation.

Workflow Parameters

This workflow accepts the following inputs:

Parameter Type Required Default Description
environment string Yes - Target environment: staging or qa
skip_tests boolean No false Skip test step (use sparingly, requires justification)
version_tag string No Git SHA or timestamp Specific version tag for the Docker image

Before starting, confirm these parameters with the user.

Technology Stack

Build & Test:

  • Node.js 20+ LTS
  • npm / yarn / pnpm
  • TypeScript 5+

Containerization:

  • Docker 24+
  • Multi-stage builds for optimization

Orchestration:

  • Kubernetes 1.28+
  • kubectl CLI
  • Namespace-based environment isolation

Registry:

  • Docker Hub, ECR, GCR, or private registry

Three-Phase Specialist Methodology

Phase 1: Pre-Deployment Validation (15%)

Before executing any deployment commands, gather context and validate readiness.

Actions:

  1. Confirm deployment parameters with user
  2. Check current git branch and status
  3. Verify Docker daemon is running
  4. Verify kubectl context is correct for target environment
  5. Check for uncommitted changes (warn if present)

Tools: Bash (git status, docker info, kubectl config current-context)

Success Criteria:

  • All parameters confirmed
  • Git working directory is clean (or user acknowledges uncommitted changes)
  • Docker daemon responsive
  • kubectl context matches target environment

Read the full file on GitHub · 366 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.

  1. 3d ago First seen · 366 lines · 83 tokens per session scan A cfcd57eceb93

Subscribe to this mod's changes

deploy-to-staging is an agent published in the GitHub repository lando-labs/cami (14 stars, last pushed 5mo ago), licensed MIT. It adds 83 tokens to every session and 2,432 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.