fix(opencode): drop skill-content edits from this PR

AGENTS.md requires evaluated adversarial testing for any skill-content
change; these three one-line harness-accuracy notes don't clear that
bar, so they are deferred to a separate evaluated change. The PR now
ships plugin, docs, and test changes only — no skill content modified.

skills/executing-plans/SKILL.md

@@ -11,7 +11,7 @@ Load plan, review critically, execute all tasks, report when complete.
 
 **Announce at start:** "I'm using the executing-plans skill to implement this plan."
 
-**Note:** Tell your human partner that Superpowers works much better with access to subagents (Claude Code, Codex CLI, Codex App, Copilot CLI, Gemini CLI, and OpenCode all qualify; see the per-platform tool refs in `../using-superpowers/references/`). If subagents are available, use superpowers:subagent-driven-development instead of this skill.
+**Note:** Tell your human partner that Superpowers works much better with access to subagents (Claude Code, Codex CLI, Codex App, Copilot CLI, and Gemini CLI all qualify; see the per-platform tool refs in `../using-superpowers/references/`). If subagents are available, use superpowers:subagent-driven-development instead of this skill.
 
 ## The Process
 

skills/subagent-driven-development/SKILL.md

@@ -374,11 +374,9 @@ scoped re-review. Five rounds maximum per task:
 
 **Rounds 1-3 — resume the original implementer.** Send it the open findings
 verbatim. Its context is intact: it knows the task, the code, and its own
-choices. If your harness can continue a live subagent, do that (e.g. OpenCode
-V2: re-invoke the `subagent` tool passing the subagent's `sessionID`; V1:
-re-dispatch `task` with the same context). Otherwise dispatch a fresh
-implementer carrying the brief path, the report-file path, and the findings —
-the report file is the persistent memory either way.
+choices. If your harness cannot send another message to a live subagent,
+dispatch a fresh implementer carrying the brief path, the report-file path,
+and the findings — the report file is the persistent memory either way.
 
 **Rounds 4-5 — dispatch a fresh implementer on a more capable model** (per
 Model Selection), with the brief path, the report-file path, the open

skills/using-git-worktrees/SKILL.md

@@ -56,8 +56,6 @@ Native tools handle directory placement, branch creation, and cleanup automatica
 
 Only proceed to Step 1b if you have no native worktree tool available.
 
-**OpenCode:** there is no agent-side worktree tool on V1 or V2 — use the git worktree fallback (Step 1b). V2's TUI worktree dialogs (new-worktree / move-session keybinds) are user-side only; you cannot invoke them from a session.
-
 ### 1b. Git Worktree Fallback
 
 **Only use this if Step 1a does not apply** — you have no native worktree tool available. Create a worktree manually using git.