菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
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.
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.
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 thread, and merge back only a compact digest.
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.
基于 SOC 职业分类
| name | code-index |
| description | 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. |
Reading entire files to find one function is the biggest avoidable input cost in a coding session. jusTokenMax keeps a lightweight symbol index of the repo so you can jump straight to a definition.
Before grepping or reading files to find where something lives, query the index:
justokenmax query parse_config # substring match on symbol name
justokenmax query Engine --kind class # filter by kind (func|class|method|...)
justokenmax query render --limit 10
Each hit is file:line [kind] signature — docstring. Read just that line
range; don't open the whole file.
justokenmax index # index the current repo -> .justokenmax/index.json
justokenmax index path/to/repo
Python is parsed precisely (via ast: functions, classes, methods, signatures,
docstrings); JS/TS/Go/Rust/Java/Ruby/C++ use fast regex heuristics. Re-run
justokenmax index after substantial code changes — the index is a snapshot, not
live. If a query says the index is missing, build it first.
Fallback if justokenmax isn't on PATH: python3 -m justokenmax query <term> /
python3 -m justokenmax index with the plugin's python/ dir on PYTHONPATH.
For exact-string or regex searches across file contents (not symbol names), plain grep is still right. The index is for "where is this symbol defined?".