Skip to main content
Protocols are reusable decision frameworks stored in .agent/skills/protocols/. Unlike workflows (which execute tasks), protocols guide how you think about problems.

What is a Protocol?

A protocol is a documented thinking pattern that you can invoke repeatedly. It answers questions like:
  • “How do I evaluate this decision?”
  • “What framework should I use for this analysis?”
  • “What questions should I ask before acting?”
Examples:
  • Protocol 123 (Einstein Protocol): Spend 11x more time defining the problem than solving it
  • Protocol 137 (Graph of Thoughts): Generate solution paths, score them, converge on the best
  • Protocol 416 (Agent Swarm): Parallelize work across multiple AI agents

Protocol vs Workflow

AspectWorkflowProtocol
PurposeExecute tasksGuide thinking
Location.agent/workflows/.agent/skills/protocols/
InvocationSlash command (/deploy)Referenced by ID (Protocol 123)
FormatChecklist of stepsFramework + decision logic
Example”Deploy to staging""55/5 Problem Definition Rule”

Protocol Structure

1. YAML Frontmatter

---
created: 2025-12-20
last_updated: 2026-01-30
---

2. Header Block

# Protocol 123: Einstein Protocol (55/5 Rule)

> **Source**: Zero-Point Codex  
> **Domain**: Decision / Problem Definition  
> **Priority**: ⭐⭐⭐ Critical

3. Core Principle

State the fundamental insight:
## Core Principle

> "If I had one hour to solve a problem, I'd spend 55 minutes defining the problem and 5 minutes solving it."

**The Ratio**: 11:1 — Problem definition is 11x more valuable than problem execution.

4. The Trigger (When to Use)

Define clear activation conditions:
## The Trigger

Use this protocol when:

- Decision involves >$10K or >6 months
- Pattern of repeated failure on similar problems
- High emotional charge suggests misalignment
- Stated goal feels disconnected from actions

5. The Mechanism (How It Works)

Provide step-by-step instructions:
## Implementation Protocol

### Phase 1: Problem Archaeology (55 min)

**Step 1: Stated vs Real Goal (10 min)**

Q: What does the user SAY they want?
Q: What do their ACTIONS optimize for?
Q: If I gave them the stated goal for free, would they take it?
Gap > 20%? → Stated goal is a proxy. Find the real one.

**Step 2: Layer Diagnosis (15 min)**

L4: Existential — "Why pursue this at all?"
L3: Archetype — "Why this specific form?"
L2: Arena — "Why this game/market?"
L1: Strategy — "How to win?"
L0: Tactics — "What specific action?"

6. Example Application

## Example Application

**Scenario**: User wants to "build an app to track fitness goals"

**55-Minute Analysis**:
- Stated goal: Fitness tracking app
- Revealed preference: User hasn't tracked fitness manually for 3 months
- Real goal: Accountability structure, not software

**5-Minute Solution**: Join a fitness group with social pressure, not build an app.

7. Anti-Patterns

## Anti-Patterns (What NOT to Do)

| Anti-Pattern | Why It Fails |
|--------------|---------------|
| "Just tell me what to do" | Skips problem definition → solves wrong problem |
| Optimizing tactics when strategy is broken | More effort, same bad outcome |
| Accepting stated goal as real | Revealed preference often differs |

Step-by-Step: Writing Your First Protocol

1

Identify a recurring decision pattern

Look for situations where you repeatedly use the same thinking framework. Examples:
  • Evaluating feature requests
  • Deciding whether to refactor code
  • Choosing between technical approaches
  • Assessing project viability
2

Choose a protocol ID

Pick a number that fits the category:
  • 0-99: Core principles
  • 100-199: Decision frameworks
  • 200-299: Verification methods
  • 300-399: Workflow patterns
  • 400-499: Architecture patterns
Create file: .agent/skills/protocols/decision/123-problem-definition.md
3

Document the core principle

What is the fundamental insight?
## Core Principle

> "[Quote or concise statement of the key idea]"

**The Rule**: [Memorable ratio, formula, or heuristic]
4

Define activation triggers

When should someone invoke this protocol?
## The Trigger

Use this protocol when:
- [Condition 1]
- [Condition 2]
- [Condition 3]
5

Break down the mechanism

Provide step-by-step instructions:
## Implementation

### Step 1: [Name]
[Instructions]

### Step 2: [Name]
[Instructions]
6

Add concrete examples

Show the protocol in action:
## Example Application

**Scenario**: [Brief description]
**Application**: [How the protocol was applied]
**Outcome**: [Result]
7

Document anti-patterns

What are common mistakes when applying this protocol?
## Anti-Patterns

| ❌ Don't | ✅ Do Instead |
|:---------|:-------------|
| [Bad pattern] | [Good pattern] |
8

Link related protocols

Connect to the knowledge graph:
## Integration Points

- **Before `/think`**: Run Layer Diagnosis
- **With Protocol 137**: Use for solution generation

## Related Protocols

- [Protocol 124: SDR Diagnosis](decision/124-sdr-diagnosis.md)
- [Protocol 137: Graph of Thoughts](workflow/137-graph-of-thoughts.md)
9

Tag for discovery

End with tags:
## Tags

#protocol #decision #problem-definition #core

Real-World Protocol: Einstein Protocol (55/5 Rule)

Here’s how Protocol 123 is structured in the Athena codebase:
# Protocol 123: Einstein Protocol (55/5 Rule)

> **Source**: Zero-Point Codex  
> **Domain**: Decision / Problem Definition  
> **Priority**: ⭐⭐⭐ Critical

## Core Principle

> "If I had one hour to solve a problem, I'd spend 55 minutes defining the problem and 5 minutes solving it."

**The Ratio**: 11:1 — Problem definition is 11x more valuable than problem execution.

## The Failure Mode

Standard Approach (Wrong):
├─ Receive problem → Jump to solutions
├─ 5 minutes: "What do we do?"
├─ 55 minutes: Implementing wrong solution
└─ Result: Efficiently solving the wrong problem ☠️

Einstein Approach (Correct):
├─ Receive problem → Interrogate assumptions
├─ 55 minutes: "What is the ACTUAL problem?"
├─ 5 minutes: Execute correct solution
└─ Result: Effort vectors toward real target ✅

## Implementation Protocol

### Phase 1: Problem Archaeology (55 min)

**Step 1: Stated vs Real Goal (10 min)**

Q: What does the user SAY they want?
Q: What do their ACTIONS optimize for? (Revealed Preference)
Q: If I gave them the stated goal for free, would they take it?
Gap > 20%? → Stated goal is a proxy. Find the real one.

### Phase 2: Solution Execution (5 min)

Only after Phase 1 completes:
1. Activate Protocol 137: Graph of Thoughts
2. Generate 3-5 solution paths
3. Execute highest EV path

Protocol Categories

Organize protocols by domain:

Decision Frameworks

  • Protocol 123: Einstein Protocol (55/5 Rule)
  • Protocol 124: SDR Diagnosis
  • Protocol 111: Premise Audit

Workflow Patterns

  • Protocol 416: Agent Swarm (Parallel Execution)
  • Protocol 419: Handoff Loop
  • Protocol 137: Graph of Thoughts

Verification Methods

  • Protocol 171: Cross-Model Validation
  • Protocol 141: Claim Atomization Audit
  • Protocol 105: Neuro-Symbolic Verification

Engineering

  • Protocol 175: TDD Workflow
  • Protocol 44: Micro-Commit Protocol

Best Practices

Start with 'why'

Every protocol should clearly state the problem it solves and the principle behind the solution.

Make it actionable

Include concrete steps, not just philosophy. Someone should be able to execute the protocol without asking for clarification.

Provide examples

Show the protocol in action with real scenarios. Abstract frameworks are hard to apply.

Version it

Use frontmatter to track creation and update dates. Protocols evolve as you learn.

Protocol Naming Conventions

Format: Protocol [ID]: [Name] ID Ranges:
  • 0-99: Core principles (Laws, Identity)
  • 100-199: Decision & analysis
  • 200-299: Verification & quality
  • 300-399: Workflow & process
  • 400-499: Architecture & systems
  • 500+: Domain-specific
File naming: [id]-[slug].md Examples:
  • 123-einstein-protocol.md
  • 416-agent-swarm.md
  • 175-tdd-workflow.md

Integration with Workflows

Protocols are referenced within workflows:
# /think — Deep Reasoning Workflow

## Phase 1: Problem Definition

- [ ] Apply **Protocol 123 (Einstein Protocol)**
- [ ] Run 55-minute problem archaeology
- [ ] Validate real vs stated goal

## Phase 2: Solution Generation

- [ ] Apply **Protocol 137 (Graph of Thoughts)**
- [ ] Generate 3-5 solution paths
- [ ] Score and converge

Common Pitfalls

❌ Don’t✅ Do Instead
Write philosophy without stepsProvide concrete, executable instructions
Skip the “when to use” sectionDefine clear activation triggers
Forget examplesShow the protocol solving a real problem
Use vague languageBe specific and measurable
Ignore anti-patternsDocument what NOT to do

Next Steps

Semantic Search

Learn how Athena finds and retrieves your protocols using triple-path retrieval

Best Practices

Operational discipline for maintaining your protocol library

Build docs developers (and LLMs) love