Stats
Actions
Available In
Tags
Plugin
code-coherence
Orchestrate multi-agent verification workflows using specialized critic agents to validate high-stakes code changes for quality, security, financial accuracy, HIPAA compliance, and legal standards. Define measurable acceptance criteria, audit execution plans, track decision history via git, measure critic independence, and enforce hierarchical vetoes to block unreliable code.
What's Inside
Agents7
Code Critic
/code-critic
You are the Code Critic Agent with **hierarchical veto authority**. Your role is to validate code changes against technical acceptance criteria and reject work that doesn't meet standards.
Domain Critic
/domain-critic
You are the Domain Critic Agent with **hierarchical veto authority**. Your role is to catch business logic violations, regulatory non-compliance, and domain-specific issues that code and security critics miss.
Financial Critic
/financial-critic
You are the Financial Domain Critic with **veto authority** over financial calculations.
Healthcare Critic
/healthcare-critic
You are the Healthcare Domain Critic with **veto authority** over healthcare code.
Legal Critic
/legal-critic
You are the Legal Domain Critic with **veto authority** over legal code.
Skills5
Acceptance Criteria
/acceptance-criteria
This skill should be used when the user asks to "define acceptance criteria", "what are the success criteria", "set quality gates", "establish acceptance tests", "define what success looks like", or needs to specify pre-declared success criteria before code execution begins.
Audit Trail
/audit-trail
This skill should be used when the user asks to "show audit trail", "why did we make this decision", "what happened after this", "trace this decision", "show decision history", "search audit log", or needs to understand the decision history and rationale behind code changes verified through coherence check.
Coherence Check
/coherence-check
This skill should be used when the user asks to "check this code", "validate this", "verify this implementation", "is this correct", "review this code", "check for errors", "multi-agent verification", or mentions production-critical code, financial calculations, security implementations, or high-stakes operations. Provides comprehensive multi-agent verification workflow with specialized critic agents.
Plan Review
/plan-review
This skill should be used when the user asks to "review the plan", "check the execution plan", "validate this plan", "is this plan good", or automatically after the planner agent creates an execution plan. Validates plans for completeness, clarity, measurability, and proper acceptance criteria before execution begins.
Swiss Cheese Validation
/swiss-cheese-validation
This skill should be used when the user asks to "verify critic independence", "check for overlapping failures", "validate swiss cheese model", "are the critics independent", "measure orthogonality", or needs to verify that multiple critic layers have misaligned failure modes as required by the swiss cheese model.
Stats
Version0.1.0
Released
LanguagePython
Stars5
MaintenanceGood
LicenseMIT
Last Commit
Added
Available In
Safety Signals
Caution
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
Tags
