From nx
Use when architectural decisions, implementations, or documentation need deep constructive critique against specs or evidence
npx claudepluginhub hellblazer/nexus --plugin nxThis skill uses the workspace's default tool permissions.
Delegates to the **substantive-critic** agent. See [registry.yaml](../../registry.yaml) for details.
Reviews design and implementation docs from analysis-process for document quality, internal consistency, and technical soundness before implementation-process.
Runs adversarial reviews on code changes, behaviors, records, evidence, or acceptance claims needing pressure-testing before acceptance.
Provides adversarial reviews of plans, specs, and design docs using Codex CLI or subagent fallback, challenging completeness, consistency, clarity, scope, and feasibility.
Share bugs, ideas, or general feedback.
Delegates to the substantive-critic agent. See registry.yaml for details.
Use the Agent tool to invoke substantive-critic:
## Relay: substantive-critic
**Task**: [what needs to be done]
**Bead**: [ID] or 'none'
### Input Artifacts
- Files: [relevant files]
### Deliverable
Critique report with prioritized findings
### Quality Criteria
- [ ] All major dimensions analyzed (structure, logic, completeness)
- [ ] Findings prioritized by impact
- [ ] Recommendations are specific and actionable
For full relay structure and optional fields, see RELAY_TEMPLATE.md.
The agent uses mcp__sequential-thinking__sequentialthinking:
Outputs generated by the substantive-critic agent:
Session Scratch (T1): Agent uses scratch tool for ephemeral working notes during the session. Flagged items auto-promote to T2 at session end.