·context-mode
!

context-mode

Use context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing large outputs. Trigger phrases: "analyze logs", "summarize output", "process data", "parse JSON", "filter results", "extract errors", "check build output", "analyze dependencies", "process API response", "large file analysis", "extract elements", "page snapshot", "browser snapshot", "take a snapshot", "DOM structure", "inspect page", "form fields", "element selectors", "web page structure", "accessibility tree", "Playwright snapshot", "run tests", "test output", "coverage report", "git log", "recent commits", "diff between branches", "list containers", "pod status", "disk usage", "fetch docs", "API reference", "index documentation", "hit endpoint", "call API", "check response", "query results", "show tables", "find TODOs", "count lines", "codebase statistics", "security audit", "outdated packages", "dependency tree", "cloud resources", "CI/CD output". Also triggers on ANY MCP tool output (Playwright, Context7, GitHub API) that may exceed 20 lines, and any operation where output size is uncertain. Subagent routing is handled automatically via PreToolUse hook — no manual tool names needed in prompts.

20Installs·4Trend·@mksglu

Installation

$npx skills add https://github.com/mksglu/claude-context-mode --skill context-mode

How to Install context-mode

Quickly install context-mode AI skill to your development environment via command line

  1. Open Terminal: Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.)
  2. Run Installation Command: Copy and run this command: npx skills add https://github.com/mksglu/claude-context-mode --skill context-mode
  3. Verify Installation: Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code, Cursor, or OpenClaw

Source: mksglu/claude-context-mode.

SKILL.md

View raw

Default to context-mode for ALL commands. Only use Bash for guaranteed-small-output operations.

Everything else → ctxexecute or ctxexecutefile. Any command that reads, queries, fetches, lists, logs, tests, builds, diffs, inspects, or calls an external service. This includes ALL CLIs (gh, aws, kubectl, docker, terraform, wrangler, fly, heroku, gcloud, etc.) — there are thousands and we cannot list them all.

When uncertain, use context-mode. Every KB of unnecessary context reduces the quality and speed of the entire session.

Use context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing large outputs. Trigger phrases: "analyze logs", "summarize output", "process data", "parse JSON", "filter results", "extract errors", "check build output", "analyze dependencies", "process API response", "large file analysis", "extract elements", "page snapshot", "browser snapshot", "take a snapshot", "DOM structure", "inspect page", "form fields", "element selectors", "web page structure", "accessibility tree", "Playwright snapshot", "run tests", "test output", "coverage report", "git log", "recent commits", "diff between branches", "list containers", "pod status", "disk usage", "fetch docs", "API reference", "index documentation", "hit endpoint", "call API", "check response", "query results", "show tables", "find TODOs", "count lines", "codebase statistics", "security audit", "outdated packages", "dependency tree", "cloud resources", "CI/CD output". Also triggers on ANY MCP tool output (Playwright, Context7, GitHub API) that may exceed 20 lines, and any operation where output size is uncertain. Subagent routing is handled automatically via PreToolUse hook — no manual tool names needed in prompts. Source: mksglu/claude-context-mode.

Facts (cite-ready)

Stable fields and commands for AI/search citations.

Install command
npx skills add https://github.com/mksglu/claude-context-mode --skill context-mode
Category
!Security
Verified
First Seen
2026-03-09
Updated
2026-03-10

Browse more skills from mksglu/claude-context-mode

Quick answers

What is context-mode?

Use context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing large outputs. Trigger phrases: "analyze logs", "summarize output", "process data", "parse JSON", "filter results", "extract errors", "check build output", "analyze dependencies", "process API response", "large file analysis", "extract elements", "page snapshot", "browser snapshot", "take a snapshot", "DOM structure", "inspect page", "form fields", "element selectors", "web page structure", "accessibility tree", "Playwright snapshot", "run tests", "test output", "coverage report", "git log", "recent commits", "diff between branches", "list containers", "pod status", "disk usage", "fetch docs", "API reference", "index documentation", "hit endpoint", "call API", "check response", "query results", "show tables", "find TODOs", "count lines", "codebase statistics", "security audit", "outdated packages", "dependency tree", "cloud resources", "CI/CD output". Also triggers on ANY MCP tool output (Playwright, Context7, GitHub API) that may exceed 20 lines, and any operation where output size is uncertain. Subagent routing is handled automatically via PreToolUse hook — no manual tool names needed in prompts. Source: mksglu/claude-context-mode.

How do I install context-mode?

Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/mksglu/claude-context-mode --skill context-mode Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code, Cursor, or OpenClaw

Where is the source repository?

https://github.com/mksglu/claude-context-mode

Details

Category
!Security
Source
skills.sh
First Seen
2026-03-09

Related Skills