Glossary · term69 of 202
effort
A per-subagent setting that controls how much a model deliberates before acting, trading thoroughness for speed, fewer tool calls, and lower spend. Left unset, it silently inherits the session's higher default.
also written as effort field · effort parameter
Related terms
execution subagentA subagent given a narrow task with a fixed output shape and a written boundary, as opposed to open-ended reasoning or planning work. Its job is to follow the spec, not to expand scope.view termmodel tierA ranking of models by relative capability and cost, from cheap and fast to expensive and frontier, used to decide which tier suits a given role in a pipeline.view termprompt cachingA billing mechanism where a stable, byte-identical prompt prefix gets reused across turns at a fraction of normal input cost, while any edit to that prefix forces a full-price rewrite.view termreasoning modelA model trained to produce an internal chain of thought before its final answer, trading extra deliberation for higher capability on hard problems.view term
At a glance
- cited by
- 4 posts
- categories
- 3
- first used
- jul 2026
Why expensive models make terrible execution subagentsSubagent model selection has one costly default. Reasoning models obey their own traces 15.6% of the time, so here is where to pin model and effort.
Every Model Release Ages Your SkillsClaude Code ignoring CLAUDE.md is often an aged file, not a model bug. See which instructions a release expires, and which lines to delete on day one.
What Opus 5's Novel-Level Reasoning Benchmark Actually MeansOpus 5 novel reasoning rests on one number, 30.2% on ARC-AGI-3, and it scores action efficiency, not problems solved. Here are the four config lines to change.
Ways to Make the Most Out of Claude Fable 5 (2026)Get more from Claude Fable 5: pick the right effort level, plan with Fable while cheaper models implement, and claw back costs with caching and batching.