response-analyzer

> **AI-consumed reference.** Optimized for Claude to read during execution. > Human-readable explanation: see [docs/architecture/HIERARCHICAL_PLANNING.md](../../../docs/architecture/HIERARCHICAL_PLANNING.md) > or [docs/getting-started/](../../../docs/getting-started/) depending on topic. # MCP Response Analyzer Reduce context bloat: write large outputs to `/tmp/aura-frog/`, load only summaries. --- ## Triggers ```toon triggers[5]{scenario,threshold,action}: Command output,>100 lines,Save to temp + summarize API response,>5KB,Save JSON + extract key fields File search results,>50 files,Save list + show top 10 Test output,>50 lines,Save full + summarize pass/fail Build output,>100 lines,Save full + show errors only ``` --- ## Directory ``` /tmp/aura-frog/ ├── responses/ # cmd-*.txt, api-*.json, search-*.txt ├── summaries/ # summary-*.md └── session/ # per-session data ``` --- ## Patterns ### Large Command Output ```bash npm test > /tmp/aura-frog/responses/test-$(date +%s).txt 2>&1 grep -E "(PASS|FAIL|Tests:|Suites:)" /tmp/aura-frog/responses/test-*.txt | tail -10 ``` ### API Response ```bash curl url > /tmp/aura-frog/responses/api-$(date +%s).json jq '{total: .data | length, first_3: .data[:3] | map(.name)}' /tmp/aura-frog/responses/api-*.json ``` ### File Search ```bash find . -name "*.ts" > /tmp/aura-frog/responses/search-$(date +%s).txt echo "Found $(wc -l < file) TypeScript files"; head -10 file ``` --- ## Token Savings ```toon savings[4]{...