deploy

A deployment workflow for sending an application to development, staging, production, or another environment using different release methods.

In plain words
What is it for?
It helps run rolling, blue-green, canary, recreate, or feature-flag deployments for containerized and serverless applications.
Why use it?
It organizes release choices and checks in one process, while allowing failed deployments to be rolled back automatically and the application to be checked afterward.

Command

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 commands/rafaelkamimura/claude-tools/deploy
Clone the repo
git clone --depth 1 https://github.com/rafaelkamimura/claude-tools
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,863 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 $0.00000 $0.02863
Opus 5 $0.00000 $0.01432
Sonnet 5 $0.00000 $0.00573
Haiku 4.5 $0.00000 $0.00286

Measured 2d ago against content hash 54c15b00b5b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deploy 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 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.

Makes network callslowCapability

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

curl -f $BLUE_URL/health || exit 1
commands/deploy.md · 492 lines

How it starts

The opening of the file, as written. The whole thing — 492 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Smart Deployment Manager

Environment-aware deployment orchestrator with support for multiple strategies, automatic rollback, and health monitoring.

Purpose

  • Deploy to dev/staging/production environments
  • Support blue-green and canary deployments
  • Automatic rollback on failure
  • Health checks and smoke tests
  • Container and serverless deployment

Workflow

Step 1: Environment Selection

  1. STOP → "Select deployment target:"

    1. Development - Local/dev environment
    2. Staging - Pre-production testing
    3. Production - Live environment
    4. Custom - Specify environment
    
    Choose environment (1-4):
    
  2. Deployment Strategy

    • STOP → "Select deployment strategy:"
    1. Rolling update - Gradual replacement
    2. Blue-green - Instant switchover
    3. Canary - Percentage-based rollout
    4. Recreate - Stop old, start new
    5. Feature flag - Toggle-based
    
    Choose strategy (1-5):
    
  3. Deployment Options

    • STOP → "Run pre-deployment tests? (y/n):"
    • STOP → "Enable automatic rollback? (y/n):"
    • STOP → "Send deployment notifications? (y/n):"

Step 2: Pre-Deployment Checks

  1. Verify Build

    # Check if build exists
    if [ ! -f "dist/index.js" ] && [ ! -d "build" ]; then
      echo "No build found. Running build..."
      npm run build || make build || cargo build --release
    fi
    
  2. Run Tests

    # Critical tests only
    npm run test:smoke || pytest tests/smoke || go test ./tests/smoke
    
  3. Check Dependencies

    # Verify all dependencies are installed
    npm ci --production || pip install -r requirements.txt --no-dev
    
  4. Security Scan

    # Quick security check
    npm audit --production || safety check
    

Step 3: Container Deployment

  1. Build Docker Image
    # Build with version tag
    VERSION=$(git describe --tags --always)
    docker build -t myapp:$VERSION .
    docker tag myapp:$VERSION myapp:latest
    

Read the full file on GitHub · 492 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. 2d ago First seen · 492 lines · 0 tokens per session scan A 54c15b00b5b5

Subscribe to this mod's changes

deploy is a command published in the GitHub repository rafaelkamimura/claude-tools (10 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,863 tokens. 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 2026-08-31.