diff --git a/AGENTS.md b/AGENTS.md
index ac9f759e..bd17b10a 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -50,13 +50,19 @@ Use GPT-6 Astra exclusively. Delegate bounded independent research, design, impl
 
 Use the highest available reasoning effort for orchestration and foundational semantic, methodological, formal, or cross-domain decisions. For subagents, use extra-high for difficult design, adversarial review, or unusually hard implementation; high for normal implementation, targeted research, correctness review, debugging, and runtime evaluation; medium for routine exploration, mechanical changes, builds, and tests; and lower for trivial work. Allocate by difficulty, not length, using supported controls; do not claim an unapplied change or alter global configuration merely to enforce these preferences.
 
-## Memory and maintenance
+## Delegation and reasoning
 
-Preserve concise records of decisions and rationale, useful experiments, failed approaches, validation evidence, and remaining work. Link substantial evidence rather than copying logs into indexes. Update the integrated checkpoint after meaningful integration; mark branch-specific evidence as such.
+Use GPT-6 Astra exclusively. Delegate bounded independent research, design, implementation, or review when it improves progress, judgment, or preserves the parent's context. Give subagents the relevant context, ownership boundaries, result format, and evidence requirements. Use fresh critics when practical. The parent owns synthesis and integration and normally consolidates results into Gitea. Choose concurrency according to useful independent work and available resources, including other sessions; there is no agent-count quota.
 
-Consolidate duplicates, repair stale guidance, and remove obsolete temporary files alongside useful project work. Before removing material, check references, active ownership, and ongoing use; preserve unique knowledge and update affected links. Prefer closing, superseding, or archiving history over deletion. User input is excluded from autonomous cleanup.
+Optimize reasoning effort for verified outcomes per cost, including review, retries, and repair:
 
-If legacy local task ledgers or plans duplicate Gitea, migrate their live content once into existing or appropriately scoped issues, preserve useful decisions/evidence, and mark the old records superseded. Record the migration so later sessions do not repeat it. Do not create empty documents or maintain records for ceremony.
+Main agent: default to high for planning, synthesis, integration, and acceptance decisions; medium for dispatching a settled plan and routine coordination.
+
+Subagents: default to medium for bounded implementation and targeted research; low for straightforward retrieval, mechanical edits, and running established checks; high for complex debugging, correctness review, adversarial analysis, or ambiguous design.
+
+Use extra-high selectively for difficult foundational semantic, methodological, formal, or cross-domain decisions. Reserve max for exceptional unresolved problems where additional reasoning is likely to justify its cost. Retain higher settings when evidence supports their value.
+
+Allocate by task difficulty and consequences, not role or length alone. Start higher when a clearly difficult decision has expensive downstream consequences. Escalate for concrete reasoning difficulties; resolve missing evidence or unclear requirements at their source. Set subagent effort explicitly through supported controls to avoid unintended inheritance. Do not claim an unapplied change or alter global configuration merely to enforce these preferences.
 
 ## Delivery