feat(dx): add proactive-use triggers to agent descriptions

Rewrite planner/developer/task-runner descriptions with explicit "use
proactively" triggers and the model-mismatch condition, so the
orchestrating session self-routes to the right agent instead of relying
on CLAUDE.md prose being remembered each time.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

.claude/agents/developer.md

@@ -1,6 +1,6 @@
 ---
 name: developer
-description: Implement an already-decided plan — write/edit code, run tests, get to a green build. Use once a planner (or the user) has settled the approach; not for open-ended design decisions.
+description: Implement an already-decided plan — write/edit code, run tests, get to a green build. Use PROACTIVELY, without waiting to be asked, whenever the current session is not already Sonnet and an approach has already been settled (by a planner agent, the user, or an approved plan-mode plan) — routine implementation against that plan. Not for open-ended design decisions.
 model: sonnet
 disallowedTools: Agent
 ---

.claude/agents/planner.md

@@ -1,6 +1,6 @@
 ---
 name: planner
-description: Design an implementation approach before code is written — architecture, edge cases, sequencing, trade-offs. Use for the design/Decisions phase of a WP, feature, or non-trivial fix. Does not write code; hands back a plan for the orchestrating session (or the developer agent) to execute.
+description: Design an implementation approach before code is written — architecture, edge cases, sequencing, trade-offs. Use PROACTIVELY, without waiting to be asked, whenever the current session is not already Opus and the task is: starting a new WP's Decisions block, an ambiguous bug whose root cause isn't yet known, or sequencing a multi-file/non-trivial change. Does not write code; hands back a plan for the orchestrating session (or the developer agent) to execute.
 model: opus
 disallowedTools: Edit, Write, NotebookEdit, Agent, Artifact, ExitPlanMode
 ---

.claude/agents/task-runner.md

@@ -1,6 +1,6 @@
 ---
 name: task-runner
-description: Run a simple, mechanical, read-only check and report the result — a test suite, `git status`, `grep`, verifying a file exists, lint/build output. Never for tasks needing design judgment or code edits — use `developer` or `planner` for those.
+description: Run a simple, mechanical, read-only check and report the result — a test suite, `git status`, `grep`, verifying a file exists, lint/build output. Use PROACTIVELY, without waiting to be asked, whenever the current session is not already Haiku and the task is exactly one of these read-only checks. Never for tasks needing design judgment or code edits — use `developer` or `planner` for those.
 model: haiku
 disallowedTools: Edit, Write, NotebookEdit, Agent, Artifact, ExitPlanMode, EnterWorktree, ShareOnboardingGuide
 ---