v0.0.1 — VS Code Extension

Every section of the sidebar,
explained.

Tokalator Pro is a real-time context budget dashboard that lives in your VS Code sidebar. Here is every panel, every metric, and every command it ships with.

🧮TokalatorPRO
LOW ~42.6K / 200.0KClaude Opus 4.6
1 open0 pinned43 turns61 in project
Claude BPE tokenizer
+~800 → ~43.4K (21.7%) · ~190 turns left
$1.01
Input~42.6K$0.213
Output (max)~32.0K$0.800
Total$1.01
Rate: $5/MTok in, $25/MTok out
$43.12of $10.00 (Copilot Pro)
Used47 turns$43.12
Remaining<$0.001
Projected/mo$339.94
Overage$33.12
Files~703
System~2.0K
Instructions~1.5K
Conversation~34.4K
Output reserve~4.0K
PRICE COMPAREBUNDLED 1H AGO Refresh
MODELWINDOWCOSTVS CURRENT
Claude Sonnet 4.6200.0K$0.188$0.225
Gemini 3.1 Pro1.0M$0.282$0.131
Claude Opus 4.7200.0K$0.413
Claude Opus 4.6200.0K$0.413current
GPT-5.41.0M$0.587+$0.173
GPT-5.51.0M$1.17+$0.760
• 43 chat turns — context may be stale
T1: ~7.8KT43: ~41.8K
+810/turn avg
🛡
Secure Workspace
Protect secrets from AI agents
📖
Generate Glossary
Compress terminology, save ~74% tokens
🧠
Generate SKILL.md
Package domain expertise for agents
Generate AI Settings
GitHub + VS Code agent configs

@tokalator Chat Commands

All commands are available through the @tokalator participant in GitHub Copilot Chat.

/countCount tokens in the active file with real BPE
/optimizeClose low-relevance tabs to free context budget
/pinPin a file to always-include (R = 1.0)
/unpinReturn a file to normal relevance scoring
/breakdownShow the 5-component token budget breakdown
/modelShow or switch the active AI model profile
/previewPreview token cost of next message before sending
/compactionShow per-turn growth and compaction recommendations
/creditsGitHub AI Credits usage, remaining, and projected cost
/secureScan workspace security and generate agent settings (Pro)
/resetReset session state and chat turn counter

Every token tracked
is a dollar saved.