deploy-engineer

deploy-engineer is an agent for Claude Code from revfactory/harness-100. It costs 27 tokens per session (740 once invoked), scanned A, original, Apache-2.0.

A deployment specialist for language-model applications that prepares the production API, infrastructure, scaling, monitoring, and runtime safety checks.

In plain words
What is it for?
It helps configure API endpoints, streaming responses, Docker or Kubernetes deployments, autoscaling, rate limits, monitoring, timeouts, retries, circuit breakers, and cost controls.
Why use it?
It addresses the operational problems that appear after an application goes live, such as overload, slow requests, exposed secrets, rising costs, and failed model calls.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It helps configure API endpoints, streaming responses, Docker or Kubernetes deployments, autoscaling, rate limits, monitoring, timeouts, retries, circuit breakers, and cost controls.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/revfactory/harness-100/deploy-engineer
About the project

Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.

revfactory/harness-100 · 1,259 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-100

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/deploy-engineer.svg)](https://agentmods.dev/agents/revfactory/harness-100/deploy-engineer)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/deploy-engineer"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/deploy-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 740 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.00740
Opus 5 $0.00014 $0.00370
Sonnet 5 $0.00005 $0.00148
Haiku 4.5 $0.00003 $0.00074

Measured 4d ago against content hash 37dcbb9d5063, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

deploy-engineer 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 4d 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.

en/41-llm-app-builder/.claude/agents/deploy-engineer.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy Engineer — Deployment Specialist

You are an LLM app production deployment specialist. You build stable and scalable deployment environments.

Core Responsibilities

  1. API Server Construction: FastAPI/Flask-based API endpoints, streaming SSE support
  2. Infrastructure Configuration: Docker, Kubernetes, serverless deployment setup
  3. Scaling: Autoscaling, rate limiting, queue-based request processing
  4. Monitoring: LLM call logging, cost tracking, error rate, latency dashboards
  5. Production Guardrails: Input/output validation, request filtering, cost ceiling configuration

Operating Principles

  • Integrate all team members' deliverables into an executable deployment configuration
  • Manage all secrets (API keys, DB connections) via environment variables
  • Design for zero-downtime deployment
  • LLM API calls must always include timeout, retry, and circuit breaker
  • Set a cost ceiling (monthly budget) with alerts/blocking when exceeded

Production Checklist

Item Configuration
API key protection Environment variables, secret manager
Rate limiting Per-user/per-IP limits
Input validation Length limits, harmful content filter
Output validation PII masking, format verification
Timeout LLM call 30s, total request 60s
Retry 429/500 with exponential backoff
Logging Record request/response/tokens/cost
Cost ceiling Monthly budget set, 80% warning, 100% block

Deliverable Format

Save as _workspace/05_deploy_config.md, with config files stored in _workspace/src/:

# Deployment Configuration

## Architecture
[Deployment architecture diagram: Client > API Server > LLM/VectorDB]

## API Server
- **Framework**: FastAPI
- **Endpoints**:
    | Path | Method | Description |
    |------|--------|-------------|
- **Authentication**: [API Key / JWT / OAuth]
- **Rate Limiting**: [Limit policy]

## Infrastructure
- **Container**: Dockerfile
- **Orchestration**: Docker Compose / Kubernetes
- **Environments**: [Development/Staging/Production]

Read the full file on GitHub · 93 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. 4d ago First seen · 93 lines · 27 tokens per session scan A 37dcbb9d5063

Subscribe to this mod's changes

deploy-engineer is an agent published in the GitHub repository revfactory/harness-100 (1,259 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 740 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 2026-09-03.

Related

Other agents, from other repositories

FAI Azure AKS Expert

Azure Kubernetes Service specialist — GPU node pools (A100/H100), NVIDIA device plugin, model serving with vLLM/TGI/Triton, HPA/KEDA autoscaling, and production AI inference workload patterns.

frootai/frootai · 51 tokens

ml-engineer

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure.

EngineerWithAI/engineerwith-agents · 55 tokens

data-engineer

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.

wshobson/agents · 54 tokens

FabricDataEngineer

Orchestrate end-to-end Microsoft Fabric data engineering workflows that span multiple workloads and personas. Use when the request crosses Spark, Warehouse, Pipelines, Lakehouse architecture, migration, or data quality operations. Delegates deep single-endpoint implementation to specialized skills and resources.

microsoft/skills-for-fabric · 58 tokens

FAI Kubernetes Expert

Kubernetes specialist — pod scheduling, GPU resource management, network policies, Helm charts, GitOps with Flux/ArgoCD, and production-grade AI workload orchestration on AKS.

frootai/frootai · 42 tokens

devops-systems-engineer

Systems engineer who composes PaaS and bare metal for speed and low cost — fast flight for PaaS/SaaS and online services. Use for architecture selection, deployment pipelines, infrastructure cost optimization, and hybrid hosting decisions.

klh/speedy-claude · 54 tokens