Skill

meta-decisions

Analyzes prompts to adapt workflows: security overrides, breaking change escalations, performance benchmarks, emergency hotfixes, and docs-only optimizations.

developer-tools

code-quality

npx claudepluginhub cubetribe/claudecode_godmode-on

Tool Access

This skill uses the workspace's default tool permissions.

Preview

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

SKILL.md

Similar Skills

workflows

Defines workflows that orchestrate agents for tasks like features, bug fixes, API changes, refactors, research, GitHub issues, and releases. Auto-selects via command patterns like 'New Feature: [X]' in CC_GodMode.

cc-godmode

orchestrator-discipline

Enforces orchestrator discipline in Claude Code multi-agent workflows via PreToolUse hooks gating file reads, diagnostic commands, and bash misuse to prevent context waste.

1 file

orchestrator-discipline

start

169

Initiates BEADS multi-agent orchestration to autonomously handle GitHub issues from creation through design review, implementation, code review, and deployment to production. Triggers on 'start issue', 'work on issue', or metaswarm mentions.

20 files

metaswarm

Stats

Stars18

Forks1

Last CommitMar 21, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Meta-Decision Logic

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

5 Meta-Decision Rules

Rule	Trigger Keywords	Workflow Adaptation
securityOverride	auth, jwt, token, password, encrypt, session	Force @validator security-focused check
breakingChangeEscalation	breaking change, deprecate, remove API, migration	Require @architect review before any change
performanceCriticalPath	performance, optimize, slow, latency, cache	Add performance benchmarks to @tester
emergencyHotfix	hotfix, urgent, critical, production down	Streamlined workflow: @builder → @validator only
documentationOnly	docs only, readme, changelog, typo fix	Skip @builder, direct to @scribe

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:

Role	Agent	Responsibility
Responsible	@builder	Does the work
Accountable	Orchestrator	Ensures completion
Reviewed by	@validator + @tester	Quality assurance
Escalated to	User	Final authority

Escalation Mechanism

When the Orchestrator cannot decide:

Ambiguous task type → Ask user for clarification
Conflicting agent outputs → Present both to user
Scope creep detected → Propose splitting into multiple tasks
Critical security concern → Stop and notify user immediately
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.