MCP レスポンス分析器

コンテキストの肥大化を削減: 大規模な出力を /tmp/aura-frog/ に書き込み、サマリーのみをコンテキストに読み込みます。

---

トリガー

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

---

ディレクトリ構成

/tmp/aura-frog/
├── responses/   # cmd-*.txt, api-*.json, search-*.txt
├── summaries/   # summary-*.md
└── session/     # per-session data

---

パターン

大規模コマンド出力

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レスポンス

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

ファイル検索

find . -name "*.ts" > /tmp/aura-frog/responses/search-$(date +%s).txt
echo "Found $(wc -l < file) TypeScript files"; head -10 file

---

トークン削減量

savings[4]{scenario,without,with,saved}:
  500-line test output,~2000,~100,95%
  Large JSON response,~5000,~200,96%
  200 file search,~800,~100,87%
  Build log,~3000,~150,95%

---

統合

workflow_integration[4]{phase,use_case,pattern}:
  Phase 2 (Test RED),Test output,Command
  Phase 4 (Review),Linter output,Command
  Phase 4 (Review),Coverage report,Command
  Any,Large API responses,API

クリーンアップ: find /tmp/aura-frog -mtime +1 -delete

---