toolshrink
Content-aware tool-result reducer: 13 reducers cut oversized output by meaning at tools/post-execute (failing tests kept, diff context dropped, JSON and CSV sampled, lint problems grouped by rule, dependency stack frames collapsed, crowded directories counted), with full originals spilled to disk behind a locator.
按内容语义压缩工具结果：13 个 reducer 在 tools/post-execute 阶段按含义裁剪超长输出（保留失败的测试、丢弃 diff 上下文、对 JSON 与 CSV 抽样、lint 问题按规则归类、依赖库的调用栈帧折叠、文件过多的目录只给计数），完整原文落盘保存并留一个定位符可取回。
How to install
dsh plugin add github:unclecode/toolshrink git clone https://github.com/unclecode/toolshrink ~/.claude/skills/toolshrink About
toolshrink **Cut large agent tool output by what it means, not by where it was cut.** I use Claude Code every day, and I always wanted to intervene in how it manages context. In the early days you could edit the session JSONL directly. Then that door closed. When DeepSeek open-sourced Harness, where everything is a plugin, I looked inside. Tool output there is cut by size: keep the head, keep the tail, drop the middle. I read Codex and pi, and they do the same. None of them look at what the text contains. That fails in a predictable way. Your test suite prints 5,000 passing lines and 3 failure…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 10
- mo. downloads
- –
- Last push
- 2026-08-19
- Created
- 2026-08-17
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- ai-agents, claude-code, context-engineering, deepseek-harness, developer-tools, dsh-plugin, llm
Related plugins
openclaw
openclaw/openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Figma-Context-MCP
GLips/Figma-Context-MCP
MCP server to provide Figma layout information to AI coding agents like Cursor
mobile-mcp
mobile-next/mobile-mcp
Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)