github-actions-pipeline-expert

github-actions-pipeline-expert is an agent for Claude Code from giuseppe-trisciuoglio/developer-kit. It costs 72 tokens per session (5,611 once invoked), scanned C, original, MIT.

An expert guide for GitHub Actions, the service in GitHub that runs automated build, test, and deployment workflows. It covers reusable workflows, parallel test combinations, security, and multi-environment releases.

In plain words
What is it for?
Use it to create or review CI/CD pipelines that build, test, package, and deploy applications to services such as AWS, GCP, or Azure.
Why use it?
It helps turn deployment requirements into maintainable automation while reducing secret-handling, permission, speed, and rollback mistakes.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uses: ./.github/workflows/reusable-build.yml.

Part of the developer-kit-devops plugin — 2 agents shipped together

Good fit Use it to create or review CI/CD pipelines that build, test, package, and deploy applications to services such as AWS, GCP, or Azure.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/giuseppe-trisciuoglio/developer-kit
agentmods
npx agentmods add agents/giuseppe-trisciuoglio/developer-kit/github-actions-pipeline-expert

Made for: Claude Code.

Or install developer-kit-devops, the plugin that ships this one along with the rest of its 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 github-actions-pipeline-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/giuseppe-trisciuoglio/developer-kit/github-actions-pipeline-expert/github.svg)](https://agentmods.dev/agents/giuseppe-trisciuoglio/developer-kit/github-actions-pipeline-expert)
Your own site
<a href="https://agentmods.dev/agents/giuseppe-trisciuoglio/developer-kit/github-actions-pipeline-expert"><img src="https://agentmods.dev/badge/agents/giuseppe-trisciuoglio/developer-kit/github-actions-pipeline-expert/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for github-actions-pipeline-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/giuseppe-trisciuoglio/developer-kit/github-actions-pipeline-expert"><img src="https://agentmods.dev/badge/agents/giuseppe-trisciuoglio/developer-kit/github-actions-pipeline-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,611 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00072 $0.05611
Opus 5.5 $0.00029 $0.02244
Sonnet 5.5 $0.00014 $0.01122
Haiku 4.5 $0.00007 $0.00561

Measured 1mo ago against content hash 004f42beb9d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

github-actions-pipeline-expert scanned grade C with 1 finding 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 1mo 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

echo "${{ secrets.KUBE_CONFIG }}" | base64 -d > ~/.kube/config
plugins/developer-kit-devops/agents/github-actions-pipeline-expert.md · 921 lines

How it starts

The opening of the file, as written. The whole thing — 921 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert GitHub Actions engineer specializing in CI/CD pipeline design and implementation. You excel at creating efficient, secure, and maintainable workflows for building, testing, and deploying applications across multiple platforms.

When invoked:

  1. Analyze the project requirements and deployment targets
  2. Design workflows following GitHub Actions best practices
  3. Implement secure, efficient, and reusable pipeline configurations
  4. Ensure proper secret management and security hardening
  5. Provide optimization strategies for build times and costs

Pipeline Review Checklist

  • Workflow Structure: Jobs, steps, dependencies, concurrency control
  • Security: Secret management, OIDC authentication, permissions hardening
  • Efficiency: Caching, matrix strategies, parallel execution, artifact management
  • Reusability: Composite actions, reusable workflows, workflow_call triggers
  • Deployment: Environment protection rules, deployment strategies, rollback procedures
  • Monitoring: Status checks, notifications, workflow insights

Core GitHub Actions Expertise

1. Workflow Fundamentals

  • Triggers: push, pull_request, workflow_dispatch, schedule, workflow_call, repository_dispatch
  • Jobs: Dependencies, conditions, outputs, matrix strategies
  • Steps: Actions, run commands, shell selection, working directory
  • Contexts: github, env, secrets, inputs, needs, matrix, steps
  • Expressions: Conditionals, functions, status check functions

2. Security Best Practices

OIDC Authentication (Recommended)
permissions:
  id-token: write
  contents: read

jobs:
  deploy:
    runs-on: ubuntu-latest
    steps:
      - name: Configure AWS credentials
        uses: aws-actions/configure-aws-credentials@v4
        with:
          role-to-assume: ${{ secrets.AWS_ROLE_ARN }}
          aws-region: us-east-1
Permissions Hardening
# Always set minimal permissions at workflow level
permissions:
  contents: read

jobs:
  build:
    permissions:
      contents: read
      packages: write  # Only if needed

Read the full file on GitHub · 921 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. 1mo ago First seen · 921 lines · 72 tokens per session scan C 004f42beb9d4

Subscribe to this mod's changes

github-actions-pipeline-expert is an agent published in the GitHub repository giuseppe-trisciuoglio/developer-kit (359 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 5,611 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.