diff --git a/agents/README.md b/agents/README.md
index 44eac4f9..b3ec4e56 100644
--- a/agents/README.md
+++ b/agents/README.md
@@ -13,8 +13,8 @@ not fleet seats. Keep changes in `/mnt/storage/src/mosaic-stack`; do not modify
 | --- | --- | --- | --- |
 | Darkwing | Hands-on engineering; collaborating seat under Sage | Pi, configured Mosaic model | `agents/darkwing/launch.sh` |
 | Dewey | Frontend design, UX, accessibility, and UI implementation | Pi, configured Mosaic model | `agents/dewey/launch.sh` |
-| Rocko | General development, investigation, testing, and review | Claude Code, Sonnet model | `agents/rocko/launch.sh` |
-| Filbert | General development, investigation, testing, and review | Pi, `openai-codex/gpt-6-astra:low` | `agents/filbert/launch.sh` |
+| Rocko | General development, investigation, testing, and review | T3 session (Claude Code, Opus 5.5, thread b84bb264, lead decision 69); launcher Claude Code, Sonnet model | `agents/rocko/launch.sh` |
+| Filbert | General development, investigation, testing, and review | T3 session (Claude Code, Opus 5.5); launcher Pi, `openai-codex/gpt-6-astra:low`, not to be used under R26 until it changes (lead decision 69) | `agents/filbert/launch.sh` |
 | Researcher | Source-grounded technical research and evidence | Pi, configured Mosaic model | `agents/researcher/launch.sh` |
 | Sage | Project lead: coordination, review, integration; earlier DYOR strategy records retained | T3 session (Claude Code); Pi launcher `zai/glm-5.3:high` retained | `agents/sage/launch.sh` |
 
diff --git a/docs/SESSIONS.md b/docs/SESSIONS.md
index 6aced10c..bfa698cf 100644
--- a/docs/SESSIONS.md
+++ b/docs/SESSIONS.md
@@ -521,3 +521,4 @@ are never rewritten or removed; corrections are new entries.
 - 2026-10-05 | rocko | row44 S2c / #1526 | Within-role citations preserved without consumption; README evidence wording fixed; 58/58 Node24+26, three mutants; eight suites pass, task26/2 Docker-disabled; review opened rev151, expected token-free post failure rev152; no commit.
 2026-10-05T23:18:04Z | Dewey (T3 Claude Code, thread 84fb346c) | row 40 S5 #1522, S2c repin | check 16 repinned to d27042fa (broker 51e03b33), verify 15/0 failed/2 N/V, 203 rows equal; probe confirms LD65 on d27042fa (citation stored, not consumed); fixture adds message.send action.allowed for 101/102; SLICE1-VIEWS.md section 10 says S2c restores them; no commit.
 2026-10-08T21:53:57Z | Sage (T3 Claude Code, thread 1ef1e4f8) | Mos 1eba59e5, Jason R1/R5/R8/R10/R17 | merge plan docs/plans/2026-10-08_refactor-to-next-merge-plan.md (pinned b8db39cf/2101c9b4, merge-tree clean); lead decision 66 (next trunk, estate Vikunja Path A replaces LD61 Path B, R1 defaults); runbook Path A text; nothing merged
+2026-10-08T22:50:00Z | Sage (T3 Claude Code, thread 1ef1e4f8) | Mos R26, lead decision 69 | Launched Rocko as T3 thread b84bb264 (claude-opus-5-5) replacing Codex/Astra thread 9b95add7; old thread idle and not messaged; row 39 unchanged; roster updated; Filbert launcher Astra pin recorded as follow-up.
diff --git a/docs/plans/2026-09-26_lead-decisions.md b/docs/plans/2026-09-26_lead-decisions.md
index 86281a4b..b0643d5f 100644
--- a/docs/plans/2026-09-26_lead-decisions.md
+++ b/docs/plans/2026-09-26_lead-decisions.md
@@ -1251,3 +1251,33 @@ which stay with him. Each item names who decided it and what happened.
       2.7.0 OpenAPI), not a bare array. The probe's `items ?? body`
       read hid it. The runbook's listing line now reads `.items[]?`,
       which also covers a null `items`.
+69. **R26 on the stack: Rocko moves to a Claude thread (2026-10-08).**
+    Source: Mos, thread 1eba59e5, relaying Jason's R26. Agentic work
+    runs on Claude models first. Codex sessions use `gpt-6.1-sol` and
+    never Astra, and T3's Codex harness defaults to `gpt-6-astra`.
+    - Stack seats in T3 on 2026-10-08: Sage, Darkwing, Dewey and
+      Filbert run Claude Opus 5.5. Researcher (9bac0794) runs Claude
+      Sonnet 5.5. Rocko (9b95add7) ran Codex on `gpt-6-astra`.
+    - Mos's option (a), a Claude thread for Rocko, chosen over (b), a
+      Codex thread on Sol. Reviews already pair Claude with Claude, and
+      a second model family would buy reviewer diversity, but R26 puts
+      Claude first, and (b) needs a reason I don't have.
+    - The new Rocko thread is b84bb264, on Opus 5.5, not the roster's
+      Sonnet. Rocko's only open row is S4, which builds
+      `mosaic decide` (it refuses inside an agent run) and the gated
+      decision DM to Jason. Under Mos's split, authority and security
+      work runs on Opus. T3 can't change a thread's model, so the
+      thread starts on the model S4 needs. This stays inside decision
+      45's limit of four Opus sessions. The roster in `agents/README.md`
+      records it.
+    - Clean point: the old thread was idle, row 39 is queued and not
+      briefed, and the earlier packets stay under `agents/rocko/work/`.
+      Nobody messages the old thread again, because that spends Astra
+      usage. Its rules carry over: no Gitea credentials, no launch, no
+      commits.
+    - Follow-up: `agents/filbert/launch.sh` pins
+      `openai-codex/gpt-6-astra:low`, and `scripts/test-darkwing-launch.mjs`
+      asserts it. Filbert runs on Claude in T3, so nothing uses that
+      launcher today. Its Astra pin conflicts with R26, and the roster
+      says not to use it until a reviewed change moves it to Claude or
+      Sol.