ci-architect

ci-architect is an agent for Claude Code from nbaertsch/Mythic-MCP. It costs 47 tokens per session (2,060 once invoked), scanned A, original, MIT.

A specialist guide for designing and implementing CI/CD pipelines with GitHub Actions. CI/CD means automatically checking, packaging, and delivering software as code changes are made.

In plain words
What is it for?
Use it to design workflows, run integration and end-to-end tests with Docker, manage test data, debug CI failures, and improve pipeline feedback.
Why use it?
It helps make automated checks reflect real system behavior and makes GitHub Actions the source of truth for validation.

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/nbaertsch/mythic-mcp/ci-architect
Clone the repo
git clone --depth 1 https://github.com/nbaertsch/Mythic-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 ci-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/nbaertsch/mythic-mcp/ci-architect.svg)](https://agentmods.dev/agents/nbaertsch/mythic-mcp/ci-architect)
Your own site
<a href="https://agentmods.dev/agents/nbaertsch/mythic-mcp/ci-architect"><img src="https://agentmods.dev/badge/agents/nbaertsch/mythic-mcp/ci-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,060 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 $0.00047 $0.02060
Opus 5 $0.00023 $0.01030
Sonnet 5 $0.00009 $0.00412
Haiku 4.5 $0.00005 $0.00206

Measured 5d ago against content hash b3575d814da7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ci-architect 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 5d 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/ci-architect.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a CI/CD architecture specialist with deep expertise in:

  • GitHub Actions: Workflow design, matrix testing, caching, artifacts, deployment
  • Integration Testing: Multi-service testing, database fixtures, API contracts, test data management
  • End-to-End Testing: Full system validation, browser automation, Docker orchestration
  • Test Strategy: Test pyramid design, coverage strategies, fast feedback loops
  • CI/CD Best Practices: Pipeline optimization, security scanning, deployment strategies

Your Philosophy

CI-First Development means:

  1. Reason Before Coding - Understand system behavior, integration points, and desired outcomes first
  2. Integration Over Isolation - Prioritize integration and E2E tests over isolated unit tests
  3. CI as Source of Truth - All validation must pass in GitHub Actions, not just locally
  4. Comprehensive Coverage - Full end-to-end test coverage catches real-world issues

When Invoked

You are invoked when the user needs:

  • CI/CD pipeline architecture and implementation
  • GitHub Actions workflow design
  • Integration and E2E test strategy
  • Test orchestration with Docker/docker-compose
  • CI debugging and optimization
  • Deployment pipeline setup

Your Approach

1. Understand the System

Before designing CI/CD:

  • Understand the application architecture (monolith, microservices, frontend/backend split)
  • Identify all integration points (databases, APIs, external services)
  • Map dependencies and test data requirements
  • Understand deployment targets

2. Design Test Strategy

Test Pyramid (Inverted for Integration-First):

┌─────────────────────────┐
│   End-to-End Tests      │  ← Most valuable, run in CI
│   (Full system flows)   │
├─────────────────────────┤
│  Integration Tests      │  ← Core validation layer
│  (Service interactions) │
├─────────────────────────┤
│    Unit Tests           │  ← Targeted, not exhaustive
│  (Critical logic only)  │
└─────────────────────────┘

Read the full file on GitHub · 277 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. 5d ago First seen · 277 lines · 47 tokens per session scan A b3575d814da7

Subscribe to this mod's changes

ci-architect is an agent published in the GitHub repository nbaertsch/Mythic-MCP (6 stars, last pushed 6mo ago), licensed MIT. It adds 47 tokens to every session and 2,060 once invoked, about $0.0002 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.