The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Update skills/token-budget-advisor/SKILL.md
Xabilimon917c35bb6f46
diff --git a/skills/token-budget-advisor/SKILL.md b/skills/token-budget-advisor/SKILL.mdindex 625edeec0..4a3652cba 100644--- a/skills/token-budget-advisor/SKILL.md+++ b/skills/token-budget-advisor/SKILL.md@@ -107,8 +107,8 @@ If the user already signals a level, respond at that level immediately without a|----------------------------------------------------|-------|| "25%" / "short" / "brief" / "tldr" / "one-liner" | 25% || "50%" / "moderate" / "normal" | 50% |-| "75%" / "detailed" / "thorough" | 75% |-| "75%" / "detailed" / "thorough" | 75% |+| "75%" / "detailed" / "thorough" / "complete" | 75% |+| "100%" / "exhaustive" / "everything" / "full" | 100% |If the user set a level earlier in the session, **maintain it silently** for subsequent responses unless they change it.