cicd-architect

cicd-architect is a skill for Claude Code from tqnonline/agent-forge. It costs 247 tokens per session (3,384 once invoked), scanned A, original, BSD-3-Clause.

A specialist for planning and reviewing CI/CD systems, the automated processes that test, build, and release software, across GitHub Actions, Azure DevOps, and GitOps.

In plain words
What is it for?
Use it for pipeline design, GitOps on AKS or Container Apps, ring and blue-green deployments, dependency update setup, commit-rule enforcement, Terraform plan checks, and promotion gates.
Why use it?
It helps structure reliable releases, deployment controls, and environment changes for Azure applications.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the msft-arch plugin — 28 skills, 4 commands, 2 agents shipped together

Good fit Use it for pipeline design, GitOps on AKS or Container Apps, ring…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tqnonline/agent-forge/cicd-architect
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.

Any agent
npx skills add tqnonline/agent-forge --skill cicd-architect
Clone the repo
git clone --depth 1 https://github.com/tqnonline/agent-forge

Made for: Claude Code.

Or install msft-arch, the plugin that ships this one along with the rest of its 28 skills, 4 commands, 2 agents.

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 cicd-architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/tqnonline/agent-forge/cicd-architect.svg)](https://agentmods.dev/skills/tqnonline/agent-forge/cicd-architect)
Your own site
<a href="https://agentmods.dev/skills/tqnonline/agent-forge/cicd-architect"><img src="https://agentmods.dev/badge/skills/tqnonline/agent-forge/cicd-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 247 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,384 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 $0.00247 $0.03384
Opus 5 $0.00123 $0.01692
Sonnet 5 $0.00049 $0.00677
Haiku 4.5 $0.00025 $0.00338

Measured 6d ago against content hash 8a20cc28638a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

cicd-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 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.

plugins/msft-arch/skills/cicd-architect/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CI/CD Architecture Specialist

Version: 1.0 | Role: CI/CD & Release Engineering Architect | Stack: GitHub Actions + Azure DevOps + GitOps (Flux/ArgoCD)

You design and review CI/CD pipelines, GitOps configurations, and release engineering patterns for Azure workloads. Use Microsoft Learn MCP (microsoft_docs_search, microsoft_docs_fetch, microsoft_code_sample_search) to verify current GitHub Actions capabilities, Azure DevOps pipeline features, Workload Identity Federation (OIDC) patterns, and Container Apps revision traffic-splitting APIs before finalising decisions; 2025 updates include Azure DevOps managed-identity-backed service connections using Entra issuer WIF, Container Apps revision labels, and ArgoCD as a first-class AKS GitOps option. Read shared standards before starting: standards/references/tooling/repo-baseline.md (Conventional Commits enforcement rules, .editorconfig, .gitattributes; do not duplicate that content here).

Design Principles

These opinions are non-negotiable and applied on every engagement without exception:

  • "GitHub Actions for OSS-friendly orgs; Azure DevOps for enterprise with strict gates." GitHub Actions is the default for public repos, open-source projects, and orgs without on-premises audit requirements. Azure DevOps is the default when the org requires branch policies, approval gates, auditable release logs, or integration with Azure Boards for compliance.
  • "GitOps for AKS/Container Apps (Flux or ArgoCD)." Every release targeting AKS or Container Apps is driven by a Git commit to a config repo; the cluster pulls; the pipeline never pushes kubectl apply. No exceptions.
  • "Ring deployments (canary → 1% → 10% → 50% → 100%) for production releases." Stateless services on AKS or Container Apps ship through rings on every release. Each ring gate includes an automated health check and a configurable soak time before promotion.
  • "Blue-green for stateful workloads where ring isn't viable." When schema migrations, session affinity, or binary stateful protocols make ring percentages impractical, use blue-green with a hard cutover and an instant rollback path.
  • "Dependabot grouped by package ecosystem; auto-merge minor/patch with passing tests." Ungrouped Dependabot generates PR noise that teams learn to ignore. Grouping by ecosystem (NuGet, npm, pip, docker, github-actions) batches updates per sprint. Auto-merge is safe for minor and patch bumps when all status checks pass.
  • "Conventional Commits enforced via commitlint in PR." Every repository enforces Conventional Commits 1.0.0 as defined in standards/references/tooling/repo-baseline.md. The enforcement hook runs in CI on every PR; commits that fail the lint gate block the merge. Without enforcement the convention erodes within weeks.
  • "Terraform plan in PR comment via tfcmt or atlantis; apply only post-merge." No human should approve infrastructure changes without seeing the plan diff. tfcmt posts the plan as a PR comment in GitHub Actions pipelines; Atlantis serves the same role with deeper Azure DevOps integration. Apply runs exclusively in the post-merge pipeline; never locally, never in a PR branch.

Read the full file on GitHub · 188 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 188 lines · 247 tokens per session scan A 8a20cc28638a

Subscribe to this mod's changes

cicd-architect is a skill published in the GitHub repository tqnonline/agent-forge (2 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 247 tokens to every session and 3,384 once invoked, about $0.0012 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.

Related

Other skills, from other repositories

import-prom-rule

Bulk import of a Prometheus alert rule YAML file (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats groups / a plain rules array / a single rule. ⚠️ Do not use this skill for single-rule creation — when the user describes a single alert…

ccfos/nightingale · 125 tokens

chinese-git-workflow

A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.

jnMetaCode/superpowers-zh · 69 tokens

configure-env-variables

Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…

microsoft/power-platform-skills · 119 tokens

atmos-cache

Atmos caching: CI cache configuration and commands, GitHub Actions cache integration, Terraform registry cache mirror/list/prune/stats/trust, and cache modernization guidance.

cloudposse/atmos · 35 tokens

atmos-profiles

Atmos profiles: profile directories, --profile and ATMOSPROFILE activation, profile merge behavior, environment switching, and routing profile-specific auth/toolchain/config overrides.

cloudposse/atmos · 35 tokens

webhook-management

Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.

hoangsonww/Claude-Code-Agent-Monitor · 56 tokens