A skill that sends big reading jobs to a cheaper AI model
agy-delegate is an that sends large, low-judgment reading work to a cheaper LLM. The goal is to keep the main agent’s context small and clean, while only bringing back a compact digest. It fits jobs with three traits: there is a lot to read, each step does not need , and the final list or summary is all that matters.
Good examples include listing all in a codebase, finding , checking TODOs, summarizing long logs, describing a whole repository’s structure, or surveying many web pages into one digest. For a quick “where is this?” search, the normal search tools are a better fit. Setup requires installing and logging into the , then placing SKILL.md in the skill folder for tools such as Claude Code, Cursor, Codex, or OpenCode.
Large jobs may need a longer print timeout than the default 5 minutes. Because the work is done by a lower-cost model, the output can be useful for collecting facts but should be spot-checked before relying on it for judgment.
Key points
- It offloads large reading tasks to a cheaper LLM.
- The main agent receives only a digest, not all raw file or page content.
- Best use cases include repo inventories, log summaries, TODO checks, and bulk web research.
- Simple lookup tasks should still use normal search tools.
- Lower-cost model output should be spot-checked when accuracy matters.