duqaXxX

Seedeep — AI skill for Claude Code

AI community

How to install Seedeep

This entry records only its repository, not the path inside it, so there is no exact command to give. Open duqaXxX/seedeep and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Seedeep does

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.

Alternatives in AI

Prompt Master — A Claude skill that writes the accurate prompts for any AI tool 4.9k ★
Paritok 4b V1 — Non-destructive compression gateway for AI coding agents 1.4k ★
Late CLI — High-performance AI agent for long-horizon tasks and local models 442 ★

README

seedeep

See deep into what Claude Code is doing.

[![npm](https://img.shields.io/badge/npm-seedeep-cb3837)](https://www.npmjs.com/package/seedeep) [![license](https://img.shields.io/badge/license-MIT-blue)](LICENSE) ![for Claude Code](https://img.shields.io/badge/for-Claude%20Code-d97757)

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.

npm i -g seedeep && seedeep     # Node or Bun; binaries below for neither

![The context window filling live while six subagents run on three models](docs/assets/hero.gif)

*One turn, from 3% to 26% of the window: six subagents on three different models, 2.9M tokens billed, 2.5M of them the same context read again.*

Why you'd run it

Eight things a Claude Code session does not report, and what `seedeep` shows instead.

A failed API call ends the turn silently. An expired login, a session limit, an overloaded server: the turn stops, the terminal keeps looking normal, and the transcript's last line is the error itself. seedeep turns the tab red, files the session under Broken, and turns the menu-bar icon red above every other signal.
An approval dialog reaches no log at all, so a session stopped on a permission prompt looks identical to one that is thinking. seedeep reads Claude Code's own live state, turns the tab amber the moment it stops, and names what is waiting to be approved.
Subagent spend is invisible from the terminal. The live tree shows each subagent as it launches: its own context filling, the model it act