This is a routing layer that intercepts commands and decides whether to run them in Bash or send them to a subagent sandbox where output stays out of your context window. The rule is simple: file operations and git commits run directly, everything else (API calls, log files, test output, CLI tools) goes through ctx_execute or ctx_execute_file. It includes special handling for browser snapshots and MCP tool output. The skill really shines when you're debugging API responses, parsing build logs, or inspecting large JSON blobs without burning through your context budget. It's opinionated about defaulting to context mode when uncertain, which makes sense if you've ever had a single kubectl describe eat half your available tokens.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.
18
skills.sh installs
185
GitHub stars
16.2K
last updated
Jun 3, 2026

Install

$ npx -y skills add mksglu/claude-context-mode --skill context-mode --agent claude-code

Installs into .claude/skills of the current project.

Files

This is a routing layer that intercepts commands and decides whether to run them in Bash or send them to a subagent sandbox where output stays out of your context window. The rule is simple: file operations and git commits run directly, everything else (API calls, log files, test output, CLI tools) goes through ctx_execute or ctx_execute_file. It includes special handling for browser snapshots and MCP tool output. The skill really shines when you're debugging API responses, parsing build logs, or inspecting large JSON blobs without burning through your context budget. It's opinionated about defaulting to context mode when uncertain, which makes sense if you've ever had a single kubectl describe eat half your available tokens.

Browse the repository on GitHub

Sponsors

Details

Repository
github.com/mksglu/claude-context-mode
First seen
Jun 3, 2026

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs