seedeep

Claude Code Memory High risk

What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each subagent on its own context window and its own model, and what the session produced. Local and read-only — your session content never leaves the machine.

实时查看 Claude Code 在你输入提示词和获得回答之间所做的操作，直接读取其已写入的日志：每次模型调用、每个工具、每个子代理及其上下文窗口和模型，以及会话产出。本地只读——你的会话内容不会离开本机。

How to install

Claude Code git clone https://github.com/duqaXxX/seedeep ~/.claude/skills/seedeep

About

seedeep *See deep into what Claude Code is doing.* Claude Code writes a session log to disk as it runs. seedeep tails that log and rebuilds the turn while it is still happening: the context window filling, every API call with its latency and token split, every tool call and its result, and each subagent folded under the spawn that launched it. The same view is there afterwards to walk through. Read-only. No proxy, no daemon, no session content leaves the machine. sh npm i -g seedeep && seedeep # Node or Bun; binaries below for neither *One turn, from 3% to 26% of the window: six subagents on t…

GitHub ↗

Recommendation signals

49 Tool quality · Based on stars, downloads, maintenance, security and docs

– User interest · Adjusted by in-site views, install copies and download clicks

49 Overall

0views

0unique visitors

0install copies

0download clicks

0outbound clicks

Links

GitHub ↗ npm ↗ Homepage ↗ Report issue ↗

Basic safety check

Findings: package.json 含 postinstall 脚本
Sources: curated:hesreallyhim/awesome-claude-code
Topics: agent-observability, agentic-coding, ai-agents, ai-coding, anthropic, bun, claude, claude-code, context-engineering, context-window, cost-tracking, developer-tools, llm, llm-observability, node, observability, subagents, token-usage, typescript, usage-tracking

Related plugins

MCP ServerClaude Code New

Score93

firecrawl-mcp-server

firecrawl/firecrawl-mcp-server

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

☆ 7.3K ↓ 492.7K Memory ↗

Claude Code New

Score88

get-shit-done

gsd-build/get-shit-done

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.

☆ 64.6K ↓ 48.5K Memory ↗

DeepSeek Harness New

Score83

hindsight

vectorize-io/hindsight

Hindsight: Agent Memory That Learns

☆ 21.5K ↓ 79 Memory ↗

Claude CodeCodex New

Score79

hivemind

activeloopai/hivemind

Hivemind turns your traces into reusable skills across agents

☆ 1.6K ↓ 2.5K Memory ↗