AdYour product here, seen by people installing AI tools every day Sponsor slots open: 12 of 12, from $249 a month

long-context-bench

Skill by jmagly · updated · ★ 224

Score 67

Benchmark compressed context against summary, direct retrieval, and provider-context baselines without enabling product integration long-context-bench is published by jmagly on GitHub.

Works withClaude CodeClaude apps Antigravity CLI
Maintenance

Last commit in the past day

Licence

MIT: permissive, fine for commercial use

Quality

Clear description, installs from GitHub, 224 stars, original repository

Security

Not checked yet. What we check

Install long-context-bench

Built from the published package, never by AI
git clone --depth 1 https://github.com/jmagly/aiwg /tmp/aiwg && mkdir -p ~/.claude/skills && cp -r /tmp/aiwg/agentic/code/addons/long-context-bench/skills/long-context-bench ~/.claude/skills/long-context-bench

Run in your terminal. Claude Code loads skills from ~/.claude/skills automatically.

Step-by-step: install long-context-bench in Claude Code

Skills can run scripts on your machine. Some need an API key: check the README.

Alternatives to long-context-bench

All alternatives →

long-context-bench: common questions

How do I install long-context-bench?

Run the command above to copy the skill into ~/.claude/skills/. Claude Code picks it up automatically.

Is long-context-bench free?

The code is published under the MIT licence. The service it connects to may have its own pricing.

Is long-context-bench safe to use?

It scores 67 of 100. Grades: maintenance A, licence A, quality B. The security check has not run for it yet. Review the code before you install. How grades work.

What are alternatives to long-context-bench?

Similar skills: memcode, pause, paper-poster, summary.