aggregate-logs
Generate LEARNINGS.md from skill execution logs over a configurable time window.
Principal-level architecture assessment against ADRs and design patterns.
> /plugin marketplace add athola/claude-night-marketHow it fires
How this command gets triggered: by you, by Claude, or both.
/architecture-reviewContext preview
What this command does when you run it.
Principal-level architecture assessment against ADRs and design patterns.
name: architecture-review description: Principal-level architecture assessment against ADRs and design patterns.
Principal-level architecture assessment against ADRs and design patterns.
/architecture-review
Invoke `Skill(pensive:architecture-review)`, which carries the assessment workflow, the ADR checks and the output format.
**Purpose**: Assess whether architecture findings warrant expert deliberation before recommendation.
**Auto-triggers when** (moderate approach):
**Checkpoint invocation** (automatic, after Risk Assessment):
Skill(attune:war-room-checkpoint) with context:
source_command: "architecture-review"
decision_needed: "Architecture recommendation for [component/PR]"
blocking_items: [
{type: "adr", description: "Violates ADR-003 without justification"},
{type: "coupling", description: "High coupling between auth and payment"}
]
files_affected: [modules under review]
profile: [from user settings, default: "default"]**War Room Questions** (when escalated):
**Response handling**:
| RS Score | Mode | Action | |----------|------|--------| | RS <= 0.40 | Express | Quick recommendation, continue | | RS 0.41-0.60 | Lightweight | Panel reviews trade-offs | | RS > 0.60 | Full Council | Full deliberation on architecture decision |
**Skip conditions**:
A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.
Generate LEARNINGS.md from skill execution logs over a configurable time window.
Analyze skill file complexity metrics and generate modularization recommendations for splitting or progressive loading.
Scaffold new Claude Code skills with brainstorming, TDD methodology, and proper frontmatter and module structure.