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
Xabilimonee3f348dcb2e
diff --git a/skills/token-budget-advisor/SKILL.md b/skills/token-budget-advisor/SKILL.mdindex c24662ed3..625edeec0 100644--- a/skills/token-budget-advisor/SKILL.md+++ b/skills/token-budget-advisor/SKILL.md@@ -107,7 +107,7 @@ 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" / "complete" | 75% |+| "75%" / "detailed" / "thorough" | 75% || "75%" / "detailed" / "thorough" | 75% |If the user set a level earlier in the session, **maintain it silently** for subsequent responses unless they change it.