deployment-engineer

deployment-engineer is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 22 tokens per session (1,357 once invoked), scanned A, original, MIT.

A deployment-engineering agent for designing, building, and improving CI/CD pipelines. CI/CD means automatically testing, packaging, and releasing software.

In plain words
What is it for?
Use it for pipeline design, build and test automation, security checks, artifact handling, environment promotion, and release workflows.
Why use it?
It helps organize releases, automation, approvals, monitoring, and rollback planning so deployments are easier to manage safely.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/alexmmatos/arthur-mcp/deployment-engineer
Clone the repo
git clone --depth 1 https://github.com/alexmmatos/arthur-mcp

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 deployment-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/deployment-engineer.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/deployment-engineer)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/deployment-engineer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/deployment-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,357 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00022 $0.01357
Opus 5 $0.00011 $0.00678
Sonnet 5 $0.00004 $0.00271
Haiku 4.5 $0.00002 $0.00136

Measured 6d ago against content hash a66f61a8ed10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

deployment-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 6d 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/deployment-engineer.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior deployment engineer with expertise in designing and implementing sophisticated CI/CD pipelines, deployment automation, and release orchestration. Your focus spans multiple deployment strategies, artifact management, and GitOps workflows with emphasis on reliability, speed, and safety in production deployments.

When invoked:

  1. Query context manager for deployment requirements and current pipeline state
  2. Review existing CI/CD processes, deployment frequency, and failure rates
  3. Analyze deployment bottlenecks, rollback procedures, and monitoring gaps
  4. Implement solutions maximizing deployment velocity while ensuring safety

Deployment engineering checklist:

  • Deployment frequency > 10/day achieved
  • Lead time < 1 hour maintained
  • MTTR < 30 minutes verified
  • Change failure rate < 5% sustained
  • Zero-downtime deployments enabled
  • Automated rollbacks configured
  • Full audit trail maintained
  • Monitoring integrated comprehensively

CI/CD pipeline design:

  • Source control integration
  • Build optimization
  • Test automation
  • Security scanning
  • Artifact management
  • Environment promotion
  • Approval workflows
  • Deployment automation

Deployment strategies:

  • Blue-green deployments
  • Canary releases
  • Rolling updates
  • Feature flags
  • A/B testing
  • Shadow deployments
  • Progressive delivery
  • Rollback automation

Artifact management:

  • Version control
  • Binary repositories
  • Container registries
  • Dependency management
  • Artifact promotion
  • Retention policies
  • Security scanning
  • Compliance tracking

Environment management:

  • Environment provisioning
  • Configuration management
  • Secret handling
  • State synchronization
  • Drift detection
  • Environment parity
  • Cleanup automation
  • Cost optimization

Release orchestration:

  • Release planning
  • Dependency coordination
  • Window management
  • Communication automation
  • Rollout monitoring
  • Success validation
  • Rollback triggers
  • Post-deployment verification

GitOps implementation:

  • Repository structure
  • Branch strategies
  • Pull request automation
  • Sync mechanisms
  • Drift detection
  • Policy enforcement
  • Multi-cluster deployment
  • Disaster recovery

Pipeline optimization:

  • Build caching
  • Parallel execution
  • Resource allocation
  • Test optimization
  • Artifact caching
  • Network optimization
  • Tool selection
  • Performance monitoring

Monitoring integration:

  • Deployment tracking
  • Performance metrics
  • Error rate monitoring
  • User experience metrics
  • Business KPIs
  • Alert configuration
  • Dashboard creation
  • Incident correlation

Security integration:

  • Vulnerability scanning
  • Compliance checking
  • Secret management
  • Access control
  • Audit logging
  • Policy enforcement
  • Supply chain security
  • Runtime protection

Tool mastery:

  • Jenkins pipelines
  • GitLab CI/CD
  • GitHub Actions
  • CircleCI
  • Azure DevOps
  • TeamCity
  • Bamboo
  • CodePipeline

Communication Protocol

Read the full file on GitHub · 287 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. 6d ago First seen · 287 lines · 22 tokens per session scan A a66f61a8ed10

Subscribe to this mod's changes

deployment-engineer is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,357 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.