justokenmax
01Plugin Claude Code
jusTokenMax — token-reduction toolkit for coding agents.
Plugin Claude Code
jusTokenMax — token-reduction toolkit for coding agents.
Plugin Claude Code
jusTokenMax — token-reduction toolkit for Claude Code. Compresses attachments (PDF→Markdown, images), verbose logs, and provides a code symbol index plus chat-branching workflows so the agent reads and writes fewer tokens.
MCP server Claude CodeCodexCursor +2
MCP server "justokenmax" as configured in Kalmantic/jusTokenMax. Runs ${CLAUDE_PLUGIN_ROOT}/python/justokenmax/mcp_server.py with python3. Needs 1 environment variable to run.
Command
Branch a self-contained sub-task into an isolated subagent context to keep the main thread cheap.
Command
Tersely rewrite a memory/context file (CLAUDE.md, notes) to cut its per-session token cost.
Command
Compress a git diff — keep real code hunks, collapse lockfile/generated/minified file diffs to one line.
Command
Build the jusTokenMax code symbol index for this repo.
Command
Mine this session for recurring corrections and save them to CLAUDE.md so future sessions don't repeat the mistakes (and waste tokens re-litigating them).
Command
Optimize attachments or logs (PDF→Markdown, image compression, log digest) to cut token cost.
Command
Show a source file's shape (signatures + line numbers, no bodies) instead of reading the whole file.
Command
Find a symbol in the code index (file:line + signature) instead of reading files.
Command
Get the original file behind an optimized artifact (reverses a jusTokenMax compression).
Command
Show lifetime token savings from jusTokenMax (attachments, logs, etc.).
Command
Switch to terse output mode to reduce the tokens the agent writes.
Hook
Runs before the agent uses a tool for Read tool calls, running python3. From Kalmantic/jusTokenMax.
Hook
Runs when the agent finishes a response, running python3. From Kalmantic/jusTokenMax.
Skill Claude CodeCodex
Compress heavy context before it costs tokens. Use when the user attaches or asks to read a PDF, scanned document, screenshot/large image, or a verbose log / build output / CI output — convert PDFs to Markdown, compress oversized images, and digest noisy logs so the same content costs a fraction of the tokens.
Skill Claude CodeCodex
Preserve prompt-prefix stability so the provider's KV cache keeps hitting, cutting cost and latency on long sessions. Use when structuring system prompts, memory files, or tool definitions, when a long session is getting expensive, or when deciding where to put changing vs stable content.
Skill Claude CodeCodex
Keep the main conversation cheap by offloading heavy sub-tasks to isolated subagent contexts. Use when a sub-task (research sweep, large-file investigation, log triage, broad search) will generate a lot of intermediate output whose conclusion is small — branch it to a subagent so the verbose work never enters the main…
Skill Claude CodeCodex
Find code by symbol name instead of reading whole files. Use when you need to locate a function, class, or method, understand where something is defined, or navigate an unfamiliar repo — query the jusTokenMax code index to get file:line + signature in a few tokens, then read only that range.
Skill Claude CodeCodex
Cut the tokens the agent WRITES, not just what it reads. Activate when the user asks for terse/concise/brief output, says responses are too long, wants to save output tokens or cost, or runs /justokenmax:terse — then answer in a compressed style that preserves all technical substance while dropping filler.
Instructions file
Claude Code instructions for Kalmantic/peakinfer-mcp, covering peakinfer mcp server - project overview, key information, architecture, what this server provides and installation.
MCP server Claude CodeCodexCursor
PeakInfer MCP Server for Claude Desktop and Claude Code. Runs locally from the @peakinfer/mcp npm package.