Stats
Actions
Tags
From flow-next
Analyzes codebase for agent readiness and proposes improvements. Use optional [path], --report-only for assessment without changes, or --fix-all to apply fixes automatically.
How this command is triggered — by the user, by Claude, or both
Slash command
/flow-next:prime [--report-only] [--fix-all] [path]flow-next/The summary Claude sees in its command listing — used to decide when to auto-load this command
# IMPORTANT: This command MUST invoke the skill `flow-next-prime` The ONLY purpose of this command is to call the `flow-next-prime` skill. You MUST use that skill now. **User request:** $ARGUMENTS Pass the user request to the skill. The skill handles all assessment and remediation logic.
flow-next-primeThe ONLY purpose of this command is to call the flow-next-prime skill. You MUST use that skill now.
User request: $ARGUMENTS
Pass the user request to the skill. The skill handles all assessment and remediation logic.
npx claudepluginhub gmickel/flow-next --plugin flow-next/code-reviewRuns enabled review agents on target files or git changes after lint/type-check/semgrep gates, producing a structured summary or JSON.
/alRuns AgentLint diagnostics across all projects with default core checks for findability, instruction quality, workability, continuity, safety, and harness. Optional deep/session analysis. Initializes config on first run.
/codebase-healthRuns parallel analysis agents on codebase (or current dir) to check structural issues, duplication, abstractions, naming, dead code, and tests. Produces prioritized health report with fix plan or auto-fix options.
/agent-native-auditAudits a codebase against 8 agent-native architecture principles, launching parallel sub-agents for scored compliance reports. Supports running a single principle when specified.
/modernization-reviewAnalyzes codebase or specified scope for outdated patterns, deprecated features, and modernization opportunities, generating a prioritized upgrade plan as Markdown report.
/reviewAnalyzes and fixes code using parallel subagents in review (changes), audit (path/codebase), or fix modes. Effort scales to input size.