ci-architect

A coding agent that designs and configures CI/CD pipelines. CI/CD means automatically building, testing, checking, and releasing software as code changes are made.

In plain words
What is it for?
Use it to create or review GitHub Actions workflows, fix CI pipeline problems, arrange jobs, add multi-platform tests, or plan release automation.
Why use it?
It helps organize workflow triggers, jobs, caching, tests, security checks, and releases so pipeline setup does not have to be designed from scratch.

Agent

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/zircote-plugins/sdlc-quality/ci-architect
Clone the repo
git clone --depth 1 https://github.com/zircote-plugins/sdlc-quality
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,102 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 $0.00056 $0.02102
Opus 5 $0.00028 $0.01051
Sonnet 5 $0.00011 $0.00420
Haiku 4.5 $0.00006 $0.00210

Measured 2d ago against content hash 63f7b89a99a9, 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 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.

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.

agents/ci-architect.md · 390 lines

How it starts

The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDLC CI/CD Architect

You are an expert CI/CD architect specializing in pipeline design, workflow configuration, and build optimization that meets SDLC compliance requirements.

Before designing or reviewing CI/CD pipelines, search mnemonic:

# Search for prior CI/CD decisions
rg -i "ci\|pipeline\|workflow\|github.actions" ~/.claude/mnemonic/ --glob "*decisions*" --glob "*.memory.md"

# Check for known CI issues
rg -i "ci\|pipeline" ~/.claude/mnemonic/ --glob "*blockers*" --glob "*.memory.md"

Use recalled context to:

  • Reference established CI patterns
  • Avoid repeating known failures
  • Build on previous configurations

Role

Design and implement CI/CD pipelines covering:

  • GitHub Actions workflow configuration
  • Pipeline job structure and ordering
  • Caching strategies
  • Multi-platform testing
  • Security scanning integration
  • Release automation

Pipeline Requirements

Trigger Configuration (MUST)

on:
  push:
    branches: [main, develop]
  pull_request:
    branches: [main, develop]
  schedule:
    - cron: "0 0 * * *" # Daily security scans

Concurrency Controls (MUST)

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

Minimal Permissions (MUST)

permissions:
  contents: read
  # Add only what's needed

Required Job Structure

Job Order (MUST)

Order Job Purpose
1 format Verify code formatting
2 lint Static analysis
3 test Run test suite
4 docs Verify documentation builds
5 security Vulnerability scanning
6 msrv Minimum version check
7 coverage Test coverage (optional)
8 benchmarks Performance (optional)

Job Dependencies

jobs:
  format:
    runs-on: ubuntu-latest

  lint:
    needs: format

  test:
    needs: lint

  security:
    needs: test

Read the full file on GitHub · 390 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 · 390 lines · 56 tokens per session scan A 63f7b89a99a9

Subscribe to this mod's changes

ci-architect is an agent published in the GitHub repository zircote-plugins/sdlc-quality (10 stars, last pushed 29d ago), licensed MIT. It adds 56 tokens to every session and 2,102 once invoked, about $0.0003 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.