Aller au contenu
TakoAPI
Retour aux skills

context-viz

par furukama

Web & Frontend Development
427Téléchargements rapportés par clawskills.sh
0Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

Visualize the current context window usage — token estimates per component (system prompt, tools, workspace files.

Description

Ce que fait ce skill

Estimates and displays a breakdown of the current context window, showing how many tokens each component (system prompt, workspace files, messages, free space) is consuming. Uses a Python script for file token estimation and the session_status tool for live context data. Also lists memory files stored on disk that aren't currently loaded.

Gives a per-component token breakdown rather than just a single usage percentage, so you can pinpoint exactly what to trim.

Quand l'utiliser

  • Checking how full the context is before a long task
  • Diagnosing which workspace files are eating the most tokens
  • Deciding when to compact or clear context
  • Auditing memory accumulation across sessions
  • Comparing token usage across different model context sizes

Exemple de workflow

ENTRÉE

User asks: how full is my context right now?

AGENT
  1. 1

    Call session_status to get model, tokens used, tokens total, and compaction count

  2. 2

    Run scripts/estimate_tokens.py against the workspace path to get per-file token estimates

  3. 3

    Subtract file tokens and system overhead from total context used to estimate message tokens

  4. 4

    Calculate free space as total minus used

  5. 5

    Render the monospace bar chart with proportional ░ blocks per component

SORTIE

A formatted context breakdown showing ~Xk tokens per component with bar lengths scaled to percentage of total context, followed by a memory-on-disk inventory grouped by category

Installation

clawhub install furukama/context-viz

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens