Skip to content

Instantly share code, notes, and snippets.

@travelhawk
Created February 17, 2026 09:08
Show Gist options
  • Select an option

  • Save travelhawk/a354f864b66611ff585f4f2f83001ace to your computer and use it in GitHub Desktop.

Select an option

Save travelhawk/a354f864b66611ff585f4f2f83001ace to your computer and use it in GitHub Desktop.
AGENTS.md — Workflow Cheat Sheet

AGENTS.md — Workflow Cheat Sheet

A practical cheat sheet for designing robust, testable, future-proof agent workflows.

This is optimized for:

  • single main agent ownership
  • explicit skill usage
  • sequential, deterministic execution
  • “good enough” optimization

Core Principles

1. One Owner, No Debates

  • One main agent owns intent and decisions
  • No role-based discussions (“designer vs architect”)
  • No swarm-style negotiation loops

Coordination happens in the workflow, not in conversation.

Reason: Role-based multi-agent choreography is token-heavy, less deterministic and often doesnt't survive model upgrades.


2. Phases, Not Roles

Think in phases with clear responsibilities.

Each phase defines:

  • goal
  • allowed skills/tools
  • expected artifact
  • exit condition

3. Skills Are Explicit

  • Skills are named and invoked
  • Never “guess” a capability
  • Prefer “use X skill” over “act as Y role”

4. Artifacts Over Opinions

Each phase produces something concrete:

  • file
  • diff
  • screenshot
  • test output
  • image

If there is no artifact, the phase is probably unclear.


Minimal AGENTS.md Template

# Agent Workflow

## Constraints
- Follow phases sequentially
- Do not skip phases
- Do not invent tools or skills
- Produce artifacts for each phase

---

## Phase 1: Plan
**Goal:** Define the approach  
**Allowed skills:** reasoning only  
**Output:** `plan.md`  
**Exit condition:** clear steps, no implementation

---

## Phase 2: Implement
**Goal:** Write code according to plan  
**Allowed skills:** filesystem, shell  
**Output:** code + tests  
**Exit condition:** build succeeds

---

## Phase 3: Validate
**Goal:** Verify behavior  
**Allowed skills:** test runner / browser automation  
**Output:** test results, logs, screenshots  
**Exit condition:** tests pass or failures explained

---

## Phase 4: Design Asset (conditional)
**Goal:** Produce visual artifact  
**Allowed skills:** image generation  
**Output:** image file (e.g. `logo.svg`)  
**Exit condition:** image matches constraints

---

## Phase 5: Finalize
**Goal:** Prepare final state  
**Allowed skills:** git (commit only)  
**Output:** commit  
**Exit condition:** clean working tree
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment