Skip to content

mcouthon/agents

Repository files navigation

AGENTS

AI-Guided Engineering — Navigate → Think → Ship

License: MIT PRs Welcome GitHub Discussions

A minimal framework for AI-assisted coding with phase-based workflows, auto-activating skills, and enforced tool safety. Works with VS Code Copilot and Claude Code.


What You Get

Component Count What It Does
Agents 4 Phase-based workflow with enforced tool restrictions and handoff buttons
Skills 9 Auto-activate based on your prompts (debug, mentor, architecture, etc.)
Instructions 5 File-type coding standards that load automatically
git clone https://github.com/mcouthon/agents.git
cd agents
./install.sh

That's it. Use /agent or the Chat menu to select agents, or just talk naturally and let skills auto-activate.


The Core Insight

"The highest leverage point is at the end of research and the beginning of the plan. A human can skim 30 seconds and provide feedback that saves hours of incorrect implementation."

This framework is built around that insight. The Explore agent is read-only—it can't accidentally edit your code. You review its research and plan, then hand off to Implement when you're ready.


The Workflow

Explore ──→ Implement ──→ Review ──→ Commit
               │            │
               │            └──→ Fix Issues ──→ (back to Implement)
               │
               └──→ Commit (skip review for small changes)
Agent Purpose Tool Access Key Handoffs
Explore Research + create plans Read + Task Write Implement
Implement Execute planned changes Full access Review, Commit
Review Verify implementation quality Read + Test Commit Changes, Fix Issues
Commit Create semantic commits Git + Read Push

Task Write: Explore can only write to .tasks/ directory—not your codebase.

Automatic state persistence: Explore saves research to .tasks/[NNN]-[task-name]/ so you can resume across sessions. Tasks are numbered sequentially (001, 002, etc.) for chronological ordering.

In-context actions: Each agent has handoff buttons for common next steps that keep your chat history and context intact. To switch agents, just @ mention them (e.g., @Implement when ready to start coding).

Handoff Buttons (In-Context Actions)

Each agent has buttons that trigger common next steps without leaving your current chat context:

Agent Button Purpose
Explore Implement Hand off to Implement agent
Plan Next Phase Detailed plan for next unplanned phase
Re-explore Investigate further
Show Plan Display phase status from task.md
Save Persist research to .tasks/
Implement Review Hand off to Review agent
Commit Hand off to Commit agent
Check for Errors Run linting and type checks
Run Tests Execute the test suite
Review Commit Changes Hand off to Commit agent
Fix Issues Hand off to Implement to address problems
Re-review Check again after fixes are applied
Check Tests Run tests and verify they pass
Commit Review Commits Show commits with git log
Amend Last Commit Amend the last commit with staged changes
Push Push commits to remote

Key benefit: These buttons keep your context and chat history. No reset, no re-explaining.


Skills (Auto-Activate)

Skills activate automatically based on what you say:

You Say Skill Activated
"This test is failing" debug
"Find code smells" tech-debt
"Clean up dead code" tech-debt
"Document the architecture" architecture
"Teach me how this works" mentor
"Challenge my approach" critic
"Create a Makefile" makefile
"Build a dashboard UI" design
"Security review this PR" security-review

No manual switching required—just ask naturally.


What AGENTS Is / Isn't

AGENTS Is AGENTS Isn't
Advisory guidance Mandatory enforcement
Phase-based workflow Magic one-shot agent
Minimal and composable Batteries-included framework
IDE-agnostic patterns Cursor/Claude-specific
Human-in-the-loop at key points Fully autonomous

Installation Details

After ./install.sh:

Component Installed To
Agents (VS Code) ~/Library/Application Support/Code/User/prompts/
Commands (Claude Code) ~/.claude/commands/
Skills ~/.copilot/skills/ (with ~/.claude/skills symlink)
Instructions ~/Library/Application Support/Code/User/prompts/
Task state gitignore Added to global gitignore (.tasks/)

Claude Code Usage

Agents are available using @agent-<Name> syntax in Claude Code:

Command Purpose
@agent-Explore <task> Research and plan
@agent-Implement Execute the plan
@agent-Review Verify changes
@agent-Commit Create semantic commits

Example workflow:

$ claude
> @agent-Explore add user authentication

[Claude researches, produces plan]

> @agent-Implement

[Claude implements based on conversation context]

> @agent-Review

[Claude reviews changes]

> @agent-Commit

[Claude creates commits]

Note: VS Code agent features like tool restrictions, model selection, and handoff buttons are not available in Claude Code. Skills work identically on both platforms.


Customization

Adding an Agent

Create .github/agents/my-agent.agent.md:

---
name: My Agent
description: What this agent does and when to use it.
tools: ["codebase", "search", "editFiles"]
model: Claude Sonnet 4 # Optional
handoffs:
  - label: Next Step
    agent: other-agent
    prompt: Continue with the next phase.
---
# My Agent Instructions

Your detailed instructions here.

Adding a Skill

Create .github/skills/my-skill/SKILL.md:

---
name: my-skill
description: >
  Trigger keywords for auto-activation: "keyword1", "keyword2".
  Focus on WHEN to use (symptoms), not WHAT it does.
---
# My Skill Instructions

Your instructions here (< 500 lines recommended).

Validating Skills (TDD for Documentation)

  1. RED - Run task WITHOUT the skill, note failures
  2. GREEN - Add skill, verify improvement
  3. REFACTOR - If agent rationalizes around it, strengthen guidance

If you didn't see it fail without the skill, you don't know if the skill helps.

Run ./install.sh after adding agents or skills.


Task Continuity

Explore persists state to .tasks/[NNN]-[task-name]/:

.tasks/001-add-auth/
  task.md                      # Research + phases + main plan
  plan/
    phase-1-config.md          # Detailed plan for phase 1 (optional)
    phase-2-user-model.md      # Detailed plan for phase 2 (optional)

Phase-Based Workflow

  1. Initial researchtask.md with research findings + phase table
  2. Plan Next Phase (optional) → detailed plan for complex phases → plan/phase-N-[name].md
  3. Implement → picks smallest planned unit (phase plan if exists, else task.md)
  4. Mark phase ✅ Done, repeat
Agent Reads Updates
Explore task.md, plan/*.md task.md, plan/*.md, phase status
Implement Phase plan or task.md Phase status (⬜→📋→🔄→✅)
Review All plan + implement

To continue a task: Just say "Continue working on [task-name]"


Agents vs Skills

Use Case Use
Need enforced tool restrictions Agent
Need handoffs between phases Agent
Want auto-activation from prompts Skill
Role-based workflow phases Agent
Specialized methodologies Skill

File Structure

.github/
├── agents/           # Workflow phases (Explore, Implement, Review, Commit)
└── skills/           # Auto-activating capabilities (debug, mentor, etc.)

instructions/         # File-type coding standards
├── global.instructions.md
├── python.instructions.md
├── typescript.instructions.md
├── testing.instructions.md
└── terminal.instructions.md

docs/
├── synthesis/        # Core principles and framework analysis
└── research/         # Research Decision Records (RDRs)

Troubleshooting

Skills not auto-activating?

  1. Run ./install.sh to ensure symlinks exist
  2. Check ~/.github/skills/ for your skills
  3. Be more explicit: "Use debug mode to investigate..."

Need to uninstall?

./install.sh uninstall

Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

Quick ways to contribute:


Further Reading

Topic Document
Core principles prevailing-wisdom.md
Framework analysis framework-comparison.md
Memory & session continuity memory-and-continuity.md
Research decisions docs/research/
12-Factor Agents docs/sources/12-factor-agents/

Why This Exists

Synthesized from multiple frameworks into something minimal and useful:

Model recommendation: Claude Opus 4.5 for heavy lifting. When Sonnet struggles, Opus delivers.

About

Collection of agentic coding instructions

Resources

License

Contributing

Stars

Watchers

Forks

Packages

No packages published

Contributors 3

  •  
  •  
  •  

Languages