Integrate 2.1 workflow and prepare release 2.2.0

skills/codex-subagent-router/SKILL.md

@@ -5,6 +5,8 @@ description: Route authorized Codex subagents across GPT-6 Luna, Sol and Astra;
 
 # Codex Subagent Router
 
+Version 2.2.0. For new general engineering sessions recommend GPT-6 Sol / medium, with high for demonstrated reasoning needs. Preserve the selected parent. Use Astra proactively for high-leverage difficult decisions, independent counterexample reviews and residual hard reasoning; neither prior failure nor a model quota is required.
+
 Make delegation useful, observable and bounded. Preserve the selected parent model. The parent owns the critical path, shared decisions, integration and final acceptance. This skill neither changes configuration nor grants external permissions.
 
 ## Trigger before routing
@@ -27,6 +29,8 @@ Spawn only P/C work with a concrete output and useful parallel benefit. Prefer u
 
 Choose the execution mechanism before a model: local tools for fixed commands/transforms, host-supported concurrent or async tools for independent I/O, and authorized children for useful independent reasoning or implementation. Waiting on a tool alone is not a reason to create an agent. Prefer a coherent outcome with acceptance over many tiny handoffs; bound ambiguity and ownership rather than prescribing every reasoning step.
 
+For queue states, integration backpressure and proactive expert formations, read [fleet scheduling](references/fleet.md).
+
 ## Proactive Luna fleet
 
 Once authorized, parallel execution is the default for ready independent work. At the first useful decomposition and after each material result or scope change, look for slices that can run alongside the parent's critical path. Dispatch those slices promptly instead of finishing the parent's entire investigation first. Do not require proof of measured speedup before a clearly useful split.
@@ -48,7 +52,7 @@ Stay local for a trivial task, no useful parallel benefit, an immediate dependen
 | Bounded classification, conversion, settled patch with fixed checks | GPT-6 Luna medium; high for local reasoning |
 | Everyday implementation, debugging, locating/correlating artifacts | GPT-6 Sol medium |
 | Bounded complex analysis, design or financial/security evidence | GPT-6 Sol medium/high |
-| Hardest independent synthesis across code, tools and research | GPT-6 Astra medium/high |
+| High-leverage difficult design, cross-system synthesis, independent high-impact counterexample review | GPT-6 Astra medium/high |
 | Shared decisions, integration and external/final gates | Current parent, serial |
 
 Luna is the first candidate when inputs are bounded, the contract is settled, correctness is cheaply checkable, and failure is contained. All four conditions matter; a short diff can still hide a shared semantic decision. Use Sol directly when investigation, design choices or cross-file causal reasoning dominate. Use Astra directly for the hardest independent synthesis when expected quality or saved rework justifies it. Do not make high/max Luna a mandatory step before Sol.
@@ -87,6 +91,8 @@ Use [evidence packets](references/evidence-packet.md) when structured evidence i
 
 ## Context and ownership discipline
 
+Read [escalation and adjudication](references/escalation.md) when planning exposes uncertainty, a key check fails, shared contracts change or acceptance has unresolved counterexamples. Preserve issue IDs and failure counts across agents. Repair missing inputs first; adjudicate by reproducible evidence, not model rank. The parent must understand and verify decisive conclusions. Continue expert rounds only with evidence-based progress, and recover to an adequate cheaper route after resolution.
+
 Load only needed references; keep long logs on disk. Avoid whole-history forks and repeating contracts, packets or prior findings. Account for parent context/reasoning, child usage, waiting, retries and integration when evaluating cost.
 
 After steering or context compaction, recover the current objective, accepted corrections, permissions, baseline, file/semantic owners and pending tool/child IDs before continuing dependent work. Retain valid completed evidence; revalidate only results affected by the change. A queued correction is not proof that a running writer has stopped or adopted it.