Skip to content
Agent

How To: Work With Agents

by TrevorPLam

AI Summary

A comprehensive guide to configuring and managing AI agents, covering role definition, permissions, monitoring, and escalation workflows. Developers and DevOps teams benefit from learning how to effectively collaborate with AI agents while maintaining governance and control.

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to set up the "How To: Work With Agents" agent in my project.

Please run this command in my terminal:
# Add AGENTS.md to your project root
curl --retry 3 --retry-delay 2 --retry-all-errors -o AGENTS.md "https://raw.githubusercontent.com/TrevorPLam/governance/main/docs/guides/HOW_TO_WORK_WITH_AGENTS.md"

Then explain what the agent does and how to invoke it.

Description

**Purpose:** Learn how to effectively work with AI agents, configure agent roles, manage permissions, monitor actions, handle HITL escalations, and troubleshoot agent issues.

Step 2: Review Agent Capabilities

Open .repo/agents/capabilities.md to see what agents can do: Capability Levels: Level 1: Basic • Modify existing code (within boundaries) • Create ADRs • Create task packets Level 2: Standard • Level 1 capabilities • Create new features • Run verification profiles Level 3: Advanced • Level 2 capabilities • Add dependencies (with ADR) • Change API contracts (with ADR) • Modify schemas (with migration plan) Level 4: Security • Level 3 capabilities • Update security (with HITL) Level 5: Release (Human Only) • Update release process • Apply waivers

Capabilities

• create_feature • modify_existing • create_adr • create_task_packet • run_verification_profiles

Capabilities

• Review code • Check quality gates • Request waivers • Approve PRs (if gates pass) • Create HITL items

Step-by-Step Guide to AI Agent Collaboration

Purpose: Learn how to effectively work with AI agents, configure agent roles, manage permissions, monitor actions, handle HITL escalations, and troubleshoot agent issues. Time Required: 30-60 minutes Skill Level: Intermediate ---

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 2mo ago
Active
AdoptionUnder 100 stars
1 ★ · Niche
DocsREADME + description
Well-documented

GitHub Signals

Stars1
Issues0
Updated2mo ago
View on GitHub
No License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Claude Code
Claude.ai