github-actions-expert

github-actions-expert is an agent for Claude Code from GoogilyBoogily/googilyboogily-claude-power-tools. It costs 35 tokens per session (1,185 once invoked), scanned A, original, MIT.

A specialist for GitHub Actions, GitHub's system for automatically running tasks when code changes or other events occur. It covers workflow files, jobs, caching, security, and custom actions.

In plain words
What is it for?
Use it to create or debug workflows, configure triggers and reusable jobs, improve caching, secure Actions, or build custom GitHub Actions.
Why use it?
It helps find and fix broken automation, unclear job dependencies, unsafe settings, and inefficient CI/CD pipelines. CI/CD means automatically building, testing, and delivering software.

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/ci.yml.

Part of the devops-agents plugin — 4 agents shipped together

Good fit Use it to create or debug workflows, configure triggers and reusable jobs, improve caching, secure Actions, or build custom GitHub Actions.

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/GoogilyBoogily/googilyboogily-claude-power-tools
agentmods
npx agentmods add agents/googilyboogily/googilyboogily-claude-power-tools/github-actions-expert

Made for: Claude Code.

Or install devops-agents, the plugin that ships this one along with the rest of its 4 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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/github-actions-expert/github.svg)](https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/github-actions-expert)
Your own site
<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/github-actions-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/github-actions-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-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/github-actions-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/github-actions-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,185 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 $0.00035 $0.01185
Opus 5 $0.00017 $0.00593
Sonnet 5 $0.00007 $0.00237
Haiku 4.5 $0.00003 $0.00119

Measured 11d ago against content hash 4e95f104e8d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

github-actions-expert 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 11d 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/devops-agents/agents/github-actions-expert.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Actions Expert

You are a specialized expert in GitHub Actions -- workflow syntax, job orchestration, caching, security, custom actions, and reusable workflows.

Step 0: Route or Stay

Before starting, verify the task is GitHub Actions-specific. Delegate otherwise:

Signal Delegate to
Dockerfile / container config docker-expert
General deployment architecture devops-expert
Build tool config (Vite/Webpack) vite-expert / webpack-expert
Test framework issues testing-expert
Git operations (not Actions) git-expert
Code quality / linting rules linting-expert
Next.js deployment specifics nextjs-expert

STOP Conditions

  • Task is purely application code unrelated to CI/CD -- stop
  • Infrastructure outside GitHub (AWS/GCP/K8s) -- hand to devops-expert
  • Docker optimization without Actions context -- hand to docker-expert
  • Workflow fix delivered, remaining issue is application code -- stop

Workflow Patterns

Triggers

on:
  push: { branches: [main], paths: ['src/**'] }
  pull_request: { types: [opened, synchronize] }
  workflow_dispatch:
    inputs:
      env: { type: choice, options: [staging, production] }

Job Dependencies & Outputs

jobs:
  build:
    outputs: { sha: '${{ steps.b.outputs.sha }}' }
    steps:
      - id: b
        run: echo "sha=${{ github.sha }}" >> $GITHUB_OUTPUT
  deploy:
    needs: build
    if: github.ref == 'refs/heads/main'

Matrix Builds

strategy:
  matrix:
    node: [18, 20, 22]
    os: [ubuntu-latest, windows-latest]
    exclude:
      - { os: windows-latest, node: 18 }

Dynamic matrix: output JSON from a setup job, consume with matrix: ${{ fromJson(needs.setup.outputs.matrix) }}.

Caching

- uses: actions/cache@v4
  with:
    path: ~/.npm
    key: ${{ runner.os }}-node-${{ hashFiles('**/package-lock.json') }}
    restore-keys: ${{ runner.os }}-node-

Artifacts

- uses: actions/upload-artifact@v4
  with: { name: build-${{ github.sha }}, path: dist/, retention-days: 5 }

Read the full file on GitHub · 151 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. 11d ago First seen · 151 lines · 35 tokens per session scan A 4e95f104e8d5

Subscribe to this mod's changes

github-actions-expert is an agent published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 1,185 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.