ccpe-system/.codex/skills/ccpe-forge/references/model-index-rules.md

11 KiB

Model Index Rules

1. Purpose

This file defines how CCPE Forge should create, audit, and maintain the Model Index.

The Model Index organizes the user's model library.

It is necessary when the user has many cognitive models extracted from articles, prompts, discussions, and agent designs.

2. What the Model Index Is

The Model Index is the map of the model library.

It tracks:

What models exist
Where they came from
What type they are
How they relate to each other
Which agents use them
Which skills execute them
Which runtimes orchestrate them
Which models are active, candidate, deprecated, or merged

The Model Index does not replace Model Cards.

It points to them.

3. Model Index Core Files

The model index should include:

model-index.md
model-taxonomy.md
model-dependency-map.md
model-usage-map.md
extraction-log.md

4. File Purposes

4.1 model-index.md

The main table of models.

It should include all known models and candidate models.

4.2 model-taxonomy.md

The classification system for models.

It defines categories such as foundational, intermediate, applied, workflow, and implicit extracted.

4.3 model-dependency-map.md

Tracks model relationships.

Examples:

Parent model
Child model
Prerequisite model
Derived model
Overlapping model
Conflicting model
Merged model
Deprecated successor

4.4 model-usage-map.md

Tracks where models are used.

Examples:

Agents
Skills
Runtimes
Prompt Cards
Committees
Knowledge workflows

4.5 extraction-log.md

Tracks model extraction events.

Examples:

Source article
Extraction date
Extracted models
Confidence
Review status
Open questions
Next action

5. Model Index Entry Fields

Each model index entry should include:

Model ID
Model Name
Aliases
Model Type
Layer
Status
Canonical Path
Source Material
Parent Models
Child Models
Related Models
Conflicting Models
Related Agents
Related Skills
Related Runtimes
Usage Notes
Review Status
Last Updated

6. Model ID

Use a stable kebab-case ID.

Example:

cognitive-imaging
giant-cognition
cognitive-prism
prediction-error-capture
argument-compression

Do not use vague IDs like:

model-1
thinking-model
good-model

7. Model Name

Use the canonical name.

Bilingual names are encouraged when useful.

Example:

认知显影术 / Cognitive Imaging

8. Aliases

Aliases help connect older documents.

Include:

Chinese name
English name
Former names
Working titles
Article-specific labels
Prompt-specific labels

9. Model Type

Use one or more:

foundational
intermediate
applied
workflow-model
implicit-extracted
candidate
deprecated

10. Layer

Layer describes the model's position in the model ecology.

Recommended values:

L0: Foundational Assumption
L1: Foundational Model
L2: Intermediate Model
L3: Applied Model
L4: Workflow / Procedure Model
L5: Output / Evaluation Lens

Example:

Cognitive Imaging = L2 Intermediate Model + L4 Workflow Model

11. Status

Use:

candidate
draft
active
rejected
merged
deprecated
archived

Default for newly extracted implicit models:

candidate

Default for structurally clear but unconfirmed models:

draft

Use active only after user confirmation.

12. Canonical Path

The canonical path points to the Model Card.

Example:

model-cards/intermediate/cognitive-imaging-model.md

For candidate models without full cards, use:

TBD

13. Source Material

Record source.

Examples:

Article title
File path
Prompt name
Conversation summary
Agent appendix

If multiple sources exist, list all important sources.

14. Parent Models

Parent models are models that provide assumptions or mechanisms.

Example:

Cognitive Imaging may depend on:
- Prediction Error
- Algorithmic Compression
- Complex Adaptive Systems
- Causal Intervention

15. Child Models

Child models are derived or applied from this model.

Example:

Cognitive Imaging may produce:
- Prediction Error Capture Skill
- Do-Operator Testing Skill
- Conspiracy Breaker Check

Related models are nearby but not parent/child.

Examples:

Cognitive Prism
Giant Cognition
Systems Thinking
Argument Compression

17. Conflicting Models

Conflicting models are models with incompatible assumptions or opposite guidance.

Use this carefully.

A model is not conflicting just because it is different.

Conflict requires actual contradiction.

List agents that use the model.

Example:

cognitive-imaging-specialist.agent.md
review-committee-chair.agent.md

List skills that execute or support the model.

Example:

cognitive-imaging.skill.md
do-operator-test.skill.md
prediction-error-capture.skill.md

List workflows that use the model.

Example:

review-committee.runtime.md
modeling-committee.runtime.md
article-to-model-extraction.runtime.md

21. Usage Notes

Usage notes explain how the model should be used.

Examples:

Use for complex adaptive systems.
Avoid using for simple linear troubleshooting.
Best used in depth-oriented review workflows.
Can be called by multiple critique agents.

22. Review Status

Review Status may differ from Status.

Use it to indicate process state:

needs-source-check
needs-user-confirmation
needs-scope-review
needs-falsification-boundary
needs-merge-review
reviewed

23. Last Updated

Use ISO date format:

YYYY-MM-DD

Do not invent dates if unknown. Use:

unknown

or leave blank if the system convention allows.

24. Model Taxonomy Rules

The taxonomy should not be too flat.

Use at least:

Foundational Models
Intermediate Models
Applied Models
Workflow Models
Implicit Extracted Models
Deprecated / Archived Models

Optional additional categories:

Causal Models
Cognitive Models
Writing Models
Review Models
Strategy Models
Knowledge Management Models
Agent Design Models
Evaluation Models

25. Dependency Mapping Rules

Dependency mapping should answer:

Which models depend on which assumptions?
Which models are applications of deeper models?
Which models overlap?
Which models should not be used together?
Which models have been merged?

Use structured bullets first.

Do not require graphical diagrams in the first version.

26. Usage Mapping Rules

Usage mapping should answer:

Which Agents use this model?
Which Skills execute this model?
Which Runtimes orchestrate this model?
Which Prompt Cards embed this model?
Which committees use this model?

This makes model maintenance possible.

If a model changes, usage mapping shows what must be updated.

27. Extraction Log Rules

Each extraction log entry should include:

Date
Source
Extractor
Models extracted
Confidence
Status
Open questions
Next action

Example:

## 2026-05-31 - Source: article-title.md

- Extracted:
  - cognitive-imaging - high confidence - draft
  - prediction-error-capture - medium confidence - candidate
- Open questions:
  - Should prediction-error-capture be a separate model or Skill?
- Next action:
  - User review before Model Index promotion.

28. Candidate Model Handling

Candidate models should be visible but not treated as canonical.

Rules:

Put candidate models in Model Index.
Mark status as candidate.
Mark confidence.
Record extraction basis.
Ask for user review.
Do not build major Agents or Skills on weak candidates without warning.

29. Active Model Handling

Active models require:

User confirmation
Model Card
Scope
Core mechanism
Failure modes
Falsification boundary
Model Index entry
Usage map if used by Agents or Skills

30. Deprecated Model Handling

Deprecated models should remain traceable.

Rules:

Mark status as deprecated.
Explain why.
Point to successor if any.
Do not delete immediately.
Update usage map to show affected Agents or Skills.

31. Merged Model Handling

When models are merged:

Mark old model as merged.
Point to canonical successor.
Explain merge reason.
Update related Agents and Skills.
Update dependency map.

32. Model Index Table Format

Use this format in model-index.md:

| Model ID | Model Name | Type | Layer | Status | Canonical Path | Source | Related Agents | Related Skills | Review Status |
|---|---|---|---|---|---|---|---|---|---|
| cognitive-imaging | 认知显影术 / Cognitive Imaging | intermediate; workflow-model | L2; L4 | draft | model-cards/intermediate/cognitive-imaging-model.md | TBD | cognitive-imaging-specialist | cognitive-imaging | needs-user-confirmation |

33. Model Taxonomy Format

Use this format in model-taxonomy.md:

# Model Taxonomy

## Foundational Models

## Intermediate Models

## Applied Models

## Workflow Models

## Implicit Extracted Models

## Deprecated / Archived Models

34. Dependency Map Format

Use this format in model-dependency-map.md:

# Model Dependency Map

## cognitive-imaging

### Parent Models
- prediction-error
- algorithmic-compression
- causal-intervention
- complex-adaptive-systems

### Child Models / Derived Skills
- prediction-error-capture
- do-operator-test
- conspiracy-breaker-check

### Related Models
- cognitive-prism
- giant-cognition

### Conflicts / Tensions
- TBD

35. Usage Map Format

Use this format in model-usage-map.md:

# Model Usage Map

## cognitive-imaging

### Agents
- cognitive-imaging-specialist.agent.md

### Skills
- cognitive-imaging.skill.md

### Runtimes
- review-committee.runtime.md

### Prompt Cards
- cognitive-imaging-specialist.prompt.md

### Notes
- Best used in depth-oriented review and complex systems analysis.

36. Model Index Quality Checklist

Before updating Model Index, check:

Is the model ID stable?
Is the model type correct?
Is the status correct?
Is the canonical path known?
Is the source recorded?
Are related models identified?
Are related agents and skills identified?
Is review status clear?
Is user confirmation needed?

37. Promotion Rules

Candidate 鈫?Draft when:

Model structure is clear.
Source is identified.
Scope and mechanism are present.

Draft 鈫?Active when:

User confirms the model.
Model Card exists.
Falsification boundary exists.
Index entry exists.
Usage mapping is updated.

Active 鈫?Deprecated when:

User rejects it.
It is superseded.
It merges into another model.
It is no longer useful.

38. Final Rule

The Model Index is not just a list.

It is the control panel for the user's cognitive model library.

It should help answer:

What models do I have?
Which ones matter most?
Which ones depend on which?
Which ones are reusable?
Which agents use them?
Which skills execute them?
Which ones need review?