Specify and plan M3b: the runner and the tools

A draft spec for the owner's review and 13 offline tasks with their given
tests: shared tool arguments and host rules in proto, the sealed fetch
target (M3a finding 14), the toolkit tools and SOCKS5 egress proxy, and
brokerd's [runner], podman argument lists, runtime and proxy lifecycle. Each
task's tests were run against a reference at that task's end state (560 to
638 tests, clippy clean); the reference is not in the repository. Adds the
runner-unavailable runbook entry and tip T23 (ETXTBSY in script tests).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

CLAUDE.md

@@ -10,7 +10,9 @@ time (M0 to M7, table in `docs/milestones.md`). M0 (measurements), M1 (workspace
 startup self-test) and M2b (sessions, the turn loop, `loopd serve`, `bxctl chat`) are done. M3 is split:
 M3a (`brokerd`'s decision path, spec `docs/specs/2026-09-18-m3a-decision-path.md`) is done and
 merged, reviewed in `docs/implementer-log.md`; its open findings (17, 18, 20, and 14, which M3b's
-first task must take) are listed there. M3b (the container runner and tools) is next to plan.
+first task must take) are listed there. M3b (the container runner and tools) is specified in
+`docs/specs/2026-09-22-m3b-runner.md` (a draft for review) and planned in `docs/plans/M3b/`
+(13 tasks, all testable offline); the image and the checks on straylight are the design model's.
 Straylight now serves Ornith as four slots over one 262,144-token pool; see
 `docs/inference-contract.md`, "Deployment change, 2026-09-20", before relying on cache behaviour.
 `docs/runbook.md` has an entry for every