Menu
Generate usage report for MiniMax and token optimization Use when: (1) /audit is invoked, (2) task relates to audit functionality.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | audit |
| description | Generate usage report for MiniMax and token optimization Use when: (1) /audit is invoked, (2) task relates to audit functionality. |
| user-invocable | true |
| context | fork |
Generate usage and cost optimization report.
~/.claude/settings.json or CLI/env varsANTHROPIC_DEFAULT_*_MODEL env vars# View stats
mmc --stats
# Detailed audit report
ralph audit
=== MiniMax Usage Audit ===
Period: Last 7 days
Model Distribution:
MiniMax M2.1: 45 queries (60%)
MiniMax-lightning: 20 queries (27%)
Claude Sonnet: 10 queries (13%)
Estimated Savings:
If all queries used Claude: ~$X.XX
Actual cost with MiniMax: ~$X.XX
Savings: ~XX%
Full orchestration workflow with swarm mode: evaluate -> clarify -> classify -> persist -> plan mode -> spawn teammates -> execute -> validate -> retrospective. Use when: (1) implementing features, (2) complex refactoring, (3) multi-file changes, (4) tasks requiring coordination. Triggers: /orchestrator, /orch, 'orchestrate', 'full workflow', 'implement feature'.
Comprehensive research skill using Zai MCP web search and native Claude Code tools
Smart Forking - Find and fork from relevant historical sessions using parallel memory search across vault, handoffs, and ledgers
Apply adversarial opposite-analysis to plans, specs, architecture, code changes, and claims. Use when the user asks for adversarial review, opposing analysis, contrarian review, red-team reasoning, or Z.ai and MiniMax cross-checks through the Ralph MCP router.
Test case mutation and variation generator for adversarial testing
Patterns for using Context7 MCP for library documentation (v2.25)