CI/CD

Configure AgentUse agents to run in GitHub Actions for automated PR reviews, comment responses, and custom workflows.

This guide uses agentuse/pr-review-agent as a comprehensive example. You can copy its workflows and agents directly to your project.

Overview

GitHub Actions can run AgentUse agents in response to repository events:

• PR Reviews: Automatic code review when PRs are opened/updated
• Comment Replies: Respond to @mentions in PR/issue comments
• Custom Workflows: Manual or scheduled agent runs

Quick Start

1. Copy Workflow Files

From the agentuse-pr-agents repository:

# Copy workflows and agents to your project
cp -r .github/agents .github/workflows your-project/.github/

This gives you:

.github/
├── workflows/
│   ├── agentuse-code-review.yml    # PR review automation
│   └── agentuse-comment-reply.yml  # @mention responses
└── agents/
    ├── code-review.agentuse        # Review agent prompt
    └── comment-reply.agentuse      # Reply agent prompt

2. Configure API Keys

Add ONE of these secrets to your repository (Settings → Secrets → Actions):

Secret Name	Provider	Get From	Best For
ANTHROPIC_API_KEY	Anthropic	console.anthropic.com	Pay-per-use
OPENAI_API_KEY	OpenAI	platform.openai.com	GPT models
OPENROUTER_API_KEY	OpenRouter	openrouter.ai	Multi-provider
CLAUDE_CODE_OAUTH_TOKEN	Claude Pro/Max	npx agentuse auth setup-github	Subscription users

For Claude Pro/Max users, run npx agentuse auth setup-github in your project directory. Follow the instructions and the command will write the secret to GitHub for you.

3. Done

Open a PR to trigger automatic review, or mention @agentuse in any comment.

Workflow Configuration

PR Code Review Workflow

File: .github/workflows/agentuse-code-review.yml

Key Configuration

on:
  pull_request:
    types: [opened, synchronize, reopened]
  workflow_dispatch:
    inputs:
      pr_number:
        description: 'PR number to review'
        required: true
        type: number

permissions:
  contents: read
  pull-requests: write

concurrency:
  group: pr-review-${{ github.event.pull_request.number }}
  cancel-in-progress: true

Environment Variables

The workflow sets these variables for the agent:

Variable	Description
GITHUB_REPOSITORY	Repo name (e.g., user/repo)
PR_NUMBER	Pull request number
BASE_REF	Target branch (e.g., main)
HEAD_REF	Source branch
GH_TOKEN	GitHub token for API access

Comment Reply Workflow

File: .github/workflows/agentuse-comment-reply.yml

Key Configuration

if: |
  github.event.issue.pull_request &&
  contains(github.event.comment.body, '@agentuse')

Context Variables

Variable	Description
COMMENT_ID	Comment ID for threading
COMMENT_AUTHOR	Who mentioned the bot
COMMENT_BODY	Full comment text

Agent File Configuration

Structure

Agent files use YAML frontmatter + markdown:

---
model: anthropic:claude-sonnet-4-6
maxSteps: 50
tools:
  bash:
    commands:
      - "gh *"
      - "git *"
  filesystem:
    - path: "${root}"
      permissions: [read]
---

# Your Agent Instructions

Instructions here in markdown...

Model Selection

Override the default model in three ways:

1. Agent file (recommended for consistency):

model: anthropic:claude-opus-4-7

2. Workflow dispatch input (one-time override):

workflow_dispatch:
  inputs:
    model:
      description: 'Model override'
      type: string

3. Environment variable (all runs):

env:
  MODEL: openai:gpt-5.2

Priority: Dispatch input → Env var → Agent file

Tool Permissions

Limit what the agent can do:

tools:
  bash:
    commands:
      - "gh *"           # GitHub CLI only
      - "git log *"      # Limited git access
  filesystem:
    - path: "src/**"     # Read source files only
      permissions: [read]

Timeout & Step Limits

maxSteps: 50  # Maximum agent steps

# In workflow
npx agentuse run agent.agentuse --timeout 300  # 5 minute timeout

Advanced Configuration

Filter PRs by Path

on:
  pull_request:
    paths:
      - 'src/**'
      - '!**/*.test.ts'

Different Models per Task

# .github/agents/quick-review.agentuse
model: anthropic:claude-haiku-4-5
maxSteps: 20

Skip Draft PRs

jobs:
  review:
    if: github.event.pull_request.draft == false

Monorepo: Pass Affected Packages

Set environment variable in workflow:

env:
  AFFECTED_PACKAGES: ${{ steps.detect.outputs.packages }}

Agent reads it at runtime:

## Step 1: Check Affected Packages

Run this command to see which packages changed:
\```bash
echo $AFFECTED_PACKAGES
\```

Focus your review on these packages only.

Custom Review Standards

Edit .github/agents/code-review.agentuse:

## Security Checks
- No hardcoded secrets
- Input validation on endpoints

## Performance
- No N+1 queries
- Pagination on large lists

Debugging

Enable debug mode in workflow:

env:
  AGENTUSE_DEBUG: true

Common issues:

Issue	Solution
Agent times out	Increase timeout: --timeout 600, reduce maxSteps, use faster model
Review not posting	Check pull-requests: write permission, verify API key
Wrong files reviewed	Check path filters, verify filesystem permissions

Security

Limit agent access in CI:

tools:
  bash:
    commands:
      - "gh pr *"  # Only PR commands, not repo admin
  filesystem:
    - path: "src/**"  # Don't expose .env, secrets/
      permissions: [read]  # Never [write] in CI

Cost Optimization

Use Cheaper Models

# For simple PRs
model: anthropic:claude-haiku-4-5  # ~$0.01/review

# For complex PRs
model: anthropic:claude-sonnet-4-6  # ~$0.05/review

Reduce Token Usage

maxSteps: 20  # Limit agent execution

In agent prompt:

Focus only on changed files. Ignore tests unless broken.
Provide concise summaries (2-3 sentences max per section).

Skip Low-Value PRs

if: |
  github.event.pull_request.draft == false &&
  github.event.pull_request.additions > 10

Reference

Common bash commands in agents:

# Get PR metadata
gh pr view $PR_NUMBER --json title,body,files

# Get diff
gh pr diff $PR_NUMBER

# Post comment
gh pr comment $PR_NUMBER --body "Review complete"

Next Steps

• Customize agents: Edit .github/agents/*.agentuse to match your workflow
• Add more workflows: Create agents for deployment, testing, documentation
• Share across repos: Use organization-level secrets and reusable workflows
• See Agent Design Patterns for advanced prompt engineering