action-builder

action-builder is a skill for Claude Code from armanzeroeight/fastagent-plugins. It costs 59 tokens per session (1,005 once invoked), scanned A, original, MIT.

A guide to creating custom GitHub Actions, which are reusable steps in GitHub's automated workflows. It covers composite, Docker, and JavaScript action structures.

In plain words
What is it for?
Use it to build custom workflow steps, package reusable automation, or create actions that combine commands, containers, or JavaScript code.
Why use it?
It helps turn repeated workflow logic into a reusable action with the appropriate implementation type.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the github-actions-toolkit plugin — 2 skills shipped together

Good fit Use it to build custom workflow steps, package reusable automation, or create actions that combine commands, containers, or JavaScript code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/armanzeroeight/fastagent-plugins/action-builder
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 armanzeroeight/fastagent-plugins --skill action-builder
Clone the repo
git clone --depth 1 https://github.com/armanzeroeight/fastagent-plugins

Made for: Claude Code.

Or install github-actions-toolkit, the plugin that ships this one along with the rest of its 2 skills.

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 action-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/armanzeroeight/fastagent-plugins/action-builder/github.svg)](https://agentmods.dev/skills/armanzeroeight/fastagent-plugins/action-builder)
Your own site
<a href="https://agentmods.dev/skills/armanzeroeight/fastagent-plugins/action-builder"><img src="https://agentmods.dev/badge/skills/armanzeroeight/fastagent-plugins/action-builder/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 action-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/armanzeroeight/fastagent-plugins/action-builder"><img src="https://agentmods.dev/badge/skills/armanzeroeight/fastagent-plugins/action-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,005 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 $0.00059 $0.01005
Opus 5 $0.00030 $0.00502
Sonnet 5 $0.00012 $0.00201
Haiku 4.5 $0.00006 $0.00101

Measured 6d ago against content hash 0f1f112a7403, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

action-builder 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/github-actions-toolkit/skills/action-builder/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Action Builder

Build custom GitHub Actions for reusable workflow logic.

Quick Start

Choose action type based on requirements:

  • Composite: Combine multiple workflow steps (simplest, no code)
  • Docker: Run containerized logic (any language, slower startup)
  • JavaScript: Fast execution, Node.js required

Instructions

Step 1: Choose Action Type

Use Composite when:

  • Combining existing actions and shell commands
  • No custom code needed
  • Fast execution required
  • Example: Setup environment with multiple tools

Use Docker when:

  • Need specific runtime environment
  • Using non-JavaScript languages
  • Complex dependencies
  • Example: Custom linting tool, data processing

Use JavaScript when:

  • Need programmatic control
  • Fast startup time critical
  • Interacting with GitHub API
  • Example: Issue labeler, PR validator

Step 2: Create Action Structure

All action types need:

action-name/
├── action.yml          # Action metadata
├── README.md           # Documentation
└── [implementation]    # Type-specific files

Step 3: Define action.yml

Required fields:

name: 'Action Name'
description: 'What the action does'
author: 'Your Name'

inputs:
  input-name:
    description: 'Input description'
    required: true
    default: 'default-value'

outputs:
  output-name:
    description: 'Output description'
    value: ${{ steps.step-id.outputs.output-name }}

runs:
  using: 'composite|docker|node16'
  # Type-specific configuration

Step 4: Implement Action Logic

For Composite Actions:

runs:
  using: 'composite'
  steps:
    - name: Step name
      run: echo "Command"
      shell: bash
    - uses: actions/checkout@v3

For Docker Actions:

runs:
  using: 'docker'
  image: 'Dockerfile'
  args:
    - ${{ inputs.input-name }}

For JavaScript Actions:

runs:
  using: 'node16'
  main: 'dist/index.js'

Step 5: Test Action Locally

Test in workflow:

jobs:
  test:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      - uses: ./  # Test local action
        with:
          input-name: 'test-value'

Read the full file on GitHub · 196 lines

Files

What ships with it

3 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 · 196 lines · 59 tokens per session scan A 0f1f112a7403

Subscribe to this mod's changes

action-builder is a skill published in the GitHub repository armanzeroeight/fastagent-plugins (29 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,005 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 2026-09-03.

Related

Other skills, from other repositories

develop-web-game

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.

netease-youdao/LobsterAI · 64 tokens

imap-smtp-email

Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.

netease-youdao/LobsterAI · 82 tokens

skin-creator

Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.

netease-youdao/LobsterAI · 48 tokens

content-planner

WeChat Official Account topic planning and content calendar management. Based on WeChat article search and trending analysis, generates differentiated topic recommendations and outputs structured content calendars. Activated when users mention "topic", "planning", "content calendar", "trending", or "what to write next…

netease-youdao/LobsterAI · 63 tokens

music-search

Search cloud drives for downloadable music resources (songs, albums, lossless audio). Use this skill when the user wants to download a specific song or album. Do NOT use for general music information, lyrics, or recommendations.

netease-youdao/LobsterAI · 47 tokens

skill-vetter

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

netease-youdao/LobsterAI · 42 tokens