Meta-Decision Logic

SkillDocs & knowledge

Meta-decision logic that adapts workflows based on task analysis — security overrides, breaking change escalation, performance paths, emergency hotfix, and documentation optimization

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Meta-Decision Logic skill

What this skill tells your AI

The instructions your AI receives, as published by cubetribe/claudecode_godmode-on in skills/meta-decisions/SKILL.md and read by ahel’s review.

The meta-decision layer analyzes user prompts and automatically adapts workflows.

5 Meta-Decision Rules

RuleTrigger KeywordsWorkflow Adaptation
securityOverrideauth, jwt, token, password, encrypt, sessionForce @validator security-focused check
breakingChangeEscalationbreaking change, deprecate, remove API, migrationRequire @architect review before any change
performanceCriticalPathperformance, optimize, slow, latency, cacheAdd performance benchmarks to @tester
emergencyHotfixhotfix, urgent, critical, production downStreamlined workflow: @builder → @validator only
documentationOnlydocs only, readme, typo fixSkip @builder, direct to @scribe. Precedence: if the change WRITES release artifacts (VERSION, CHANGELOG.md beyond the sprint-integration [Unreleased] entry), the release-artifact risk signal wins and the release law applies (docs/orchestrator/VERSIONING.md)

Decision Flow

User Prompt Received
    ↓
analyze-prompt.js evaluates:
    ↓
┌─ Security keywords? → securityOverride
├─ Breaking change? → breakingChangeEscalation
├─ Performance? → performanceCriticalPath
├─ Emergency? → emergencyHotfix
└─ Docs only? → documentationOnly
    ↓
None matched → Standard workflow selection

Architecture Decision Records (ADR)

Significant decisions are logged in DECISIONS.md:

## ADR-[NUMBER]: [Title]

**Date:** YYYY-MM-DD
**Status:** Accepted / Superseded / Deprecated
**Context:** [Why this decision was needed]
**Decision:** [What was decided]
**Consequences:** [Impact of the decision]

RARE Responsibility Matrix

For complex decisions, use the RARE matrix:

RoleAgentResponsibility
Responsible@builderDoes the work
AccountableOrchestratorEnsures completion
Reviewed by@validator + @testerQuality assurance
Escalated toUserFinal authority

Escalation Mechanism

When the Orchestrator cannot decide:

  1. Ambiguous task type → Ask user for clarification
  2. Conflicting agent outputs → Present both to user
  3. Scope creep detected → Propose splitting into multiple tasks
  4. Critical security concern → Stop and notify user immediately
  5. Resource limit approaching → Suggest /compact and restart

Issue Analysis Enhancement

When processing issues, the meta-layer adds:

{
  "type": "feature|bug|enhancement",
  "complexity": "low|medium|high",
  "areas": ["api", "ui", "backend"],
  "meta_rules_triggered": ["securityOverride"],
  "workflow_adaptation": "Added security-focused @validator check"
}

Emergency Hotfix Workflow

When emergencyHotfix is triggered:

User: "Hotfix: production login broken"
    ↓
@builder (immediate fix)
    ↓
@validator (security + unit tests only)
    ↓
DONE (skip @tester, @scribe — speed over process)

Post-hotfix: Schedule a follow-up with full quality gates.

Signals

GitHub stars
51
Forks
8
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
meta-decisions
Source
github.com/cubetribe/claudecode_godmode-on