on main help sign in
feat(init-cmd): mention progressive disclosure (#1786)

I found Crush was often both too verbose and too terse than I'd like in different ways when generating the AGENTS.md. This is an attempt to improve the relevancy of the information it mentions. As just one example, tabs vs spaces is obvious from the first file read, so mentioning that style preference in AGENTS.md just wastes tokens. Since adding this line, I haven't noticed it including trivial details like that! Though I've been using this since Dec 20 and liking it, I've mostly used it and had good results with Claude models. I've not tried it with GPT or GLM or others yet.

commitd161cbcf5d5500286b3526951e72fcfeeefeb6d5 authorAmolith <amolith@secluded.site> dateTue 31 Mar 2026, 13:45 (7 months ago) parentcda2719
1 file changed+2
internal/agent/templates/initialize.md.tpl+2
internal/agent/templates/initialize.md.tpl+2
@@ -22,6 +22,8 @@ Analyze this codebase and create/update **{{.Config.Options.InitializeAs}}** to
2222- Important gotchas or non-obvious patterns
2323- Any project-specific context from existing rule files
2424
25+**Note:** LLM agents learn and adapt to their context as they obtain it, so mentioning obvious details they would immediately pick up from reading a file or two is actively detrimental. Keep the principles of progressive disclosure in mind and focus primarily on non-obvious knowledge that saves the agent from trial-and-error discovery: gotchas, implicit conventions, commands with surprising flags, and context that isn't self-evident from the code in a single file.
26+
2527**Format**: Clear markdown sections. Use your judgment on structure based on what you find. Aim for completeness over brevity - include everything an agent would need to know.
2628
2729**Critical**: Only document what you actually observe. Never invent commands, patterns, or conventions. If you can't find something, don't include it.