If you're using context-mode to offload data into a sandbox knowledge base, this shows you exactly how much token budget you're saving. It displays total tokens consumed, your savings ratio, and a per-tool breakdown of what's been indexed. The output is verbose by design: full tables pasted directly into the response so you can see the numbers without extra clicks. It's read-only, so you can check stats anytime without worrying about accidentally nuking your knowledge base. The real value is in that savings multiplier, useful when you're debugging why a session hasn't blown through your context window yet or deciding whether context-mode is pulling its weight.

skills.sh installs
1.8K
GitHub stars
33.8K
last updated
Aug 21, 2026

Install

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

Installs into .claude/skills of the current project.

Files

Call the ctx_stats tool and show the text block of its reply to the user unchanged, inside a code block so the columns stay aligned. Add one sentence under it that names the largest saving.

Sponsors

Details

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

More from mksglu/context-mode

All 7

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