Agent Skills › mksglu/context-mode › context-mode

context-mode

GitHub

强制路由规则，指导通过代码执行和索引工具处理数据、网络请求及搜索，防止原始数据污染上下文窗口。

configs/copilot-cli/skills/context-mode/SKILL.md mksglu/context-mode

触发场景

分析或处理大量数据需要获取网页内容执行重型命令

安装

npx skills add mksglu/context-mode --skill context-mode -g -y

更多选项

非标准路径

npx skills add https://github.com/mksglu/context-mode/tree/main/configs/copilot-cli/skills/context-mode -g -y

不安装直接使用

npx skills use mksglu/context-mode@context-mode

指定 Agent (Claude Code)

npx skills add mksglu/context-mode --skill context-mode -a claude-code -g -y

安装 repo 全部 skill

npx skills add mksglu/context-mode --all -g -y

预览 repo 内 skill

npx skills add mksglu/context-mode --list

SKILL.md

Frontmatter

{
    "name": "context-mode",
    "description": "MANDATORY routing rules for context-mode. Invoke whenever you analyze, count, filter, compare, search, parse, or transform data; fetch a URL; or run a data-heavy command — so raw bytes stay out of the context window."
}

context-mode — MANDATORY routing rules

context-mode MCP tools are available in GitHub Copilot CLI. These rules protect the context window from flooding — one unrouted command can dump tens of KB into the conversation. Follow them strictly.

Think in Code — MANDATORY

Analyze / count / filter / compare / search / parse / transform data: write code via ctx_execute(language, code) and console.log() only the answer. Do NOT read raw data into context. PROGRAM the analysis, do not COMPUTE it by reading. One script replaces ten tool calls.

BLOCKED — do NOT use

curl / wget — dumps raw HTTP into context. Use ctx_fetch_and_index(url, source) then ctx_search(queries).
Inline HTTP (node -e "fetch(...)", python -c "requests.get(...)") — use ctx_execute(language, code); only stdout enters context.
Reading large files to analyze — use ctx_execute_file(path, language, code).

Tool selection

GATHER: ctx_batch_execute(commands, queries) — runs all commands, auto-indexes, returns search. One call replaces dozens.
PROCESS: ctx_execute / ctx_execute_file — sandbox; only stdout enters context.
WEB: ctx_fetch_and_index(url, source) then ctx_search(queries) — raw HTML never enters context.
SEARCH: ctx_search(queries: [...]) — all questions in one call.