agentmods.dev

munhq/distil

Measure what context compression actually costs an LLM agent: where a session's tokens go, and whether a rewrite pays for the prompt cache it invalidates. Rust crate, MCP server and benchmark harness.

Open on GitHub
1Stars on the repository
5Mods indexed here, across every type
4d agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied
Sort RelevanceRecently updatedFewest tokensSecurity gradeRepo starsStars this weekTop rated 1 mods

distil

01

munhq/distil

Skill Claude CodeCodex

Decide whether to compress an agent's context, and compress it when the answer is yes. Use when a conversation is approaching the context window limit, when a request has failed or is about to fail for length, or when the user asks to compact, shrink or trim the context. Also use to measure where a session's tokens…

1 4d ago A 81 tokens