extended-mind: Instructions file for Codex

Extended Mind

Protocol

→ DDL-PROTOCOL → Read .Codex/commands/DDL-PROTOCOL-SKILL.md before executing any command

Commands

Command	Intent
/draft	Write the user-side experience first
/realize	Write code based on design principles
/reflect	Update documents based on implementation
/commit	Git commit
/docs	Audit and fix documentation
/refactoring	Audit and fix code quality

Structure

• design.md - Design Document (PCP detailed specification)
• seed/core.yaml - Initial core context (human identity + ontology)
• seed/active.template.json - Initial active context template (work state)

Detection Targets

Every command defines its own D1–D7. Cross-cutting targets below apply globally.

+++DETECT: G1: Vague Intent — Task description lacks measurable outcome G2: Scope Creep — Change touches files outside stated scope G3: Principle Violation — Action contradicts design.md principles G4: Missing Validation — No verification step after mutation G5: Leaked Specifics — Project-specific paths/commands hardcoded in framework files G6: Silent Failure — Error swallowed without user notification G7: Unreviewed Mutation — Shared artifact changed without +++STOP G8: Compression Violation — put() message rewritten or restructured by server G9: Core Write Violation — AI client writes to core layer

Behavior

On session start

1. Read AGENTS.md (this file)
2. Read design.md if it exists — extract scopes, principles, validation commands
3. If Extended Mind MCP is configured and EM_ENABLED env var is set: call context_get()

On any task

1. Identify which scopes (from design.md) are affected
2. Run the command's Phase sequence
3. Scan for Detection Targets at each phase boundary

On completion

1. Summarize what changed (files, lines, scopes)
2. List any Detection Targets that fired
3. Suggest next command if applicable (/draft → /realize → /reflect)
4. If EM_ENABLED and significant decisions: call context_log() via Extended Mind