From crux
Lists active Crux decisions from project graph with rationales, constraints, establishment turns, and confidence scores. Shows superseded decisions separately.
How this skill is triggered — by the user, by Claude, or both
Slash command
/crux:crux-decisionsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read the current Crux graph from `.claude/.crux/sessions/` in the project root (find the most recent `.json` file, or the one matching the current session) and list all DECISION-type atoms with status ACTIVE.
Read the current Crux graph from .claude/.crux/sessions/ in the project root (find the most recent .json file, or the one matching the current session) and list all DECISION-type atoms with status ACTIVE.
For each decision, show:
dependsOn links to RATIONALE atoms)dependsOn links to CONSTRAINT atoms)Also show any SUPERSEDED decisions (with what superseded them) in a separate section.
If no decisions are tracked, report that no decisions have been captured yet. Remind the user that Crux captures decisions automatically during conversation.
npx claudepluginhub akashp1712/claude-marketplace --plugin cruxQueries AI decision trails for code reviews (CRs), gates, analysis (intent/change/risk/autonomy), architecture decisions (ADR), and timelines. Audits judgments with confidence scores, processes, and context navigation.
Guides creation of decision records with full context, alternatives, rationale, and revisit conditions. Auto-links related PRDs, strategy docs, OKRs. Useful for product decision documentation.
Searches stored memories and decisions using MCP tools to answer questions about past learnings, architectural choices, patterns, and project context like 'what testing framework did we decide on?' or 'ESM import issues?'