Merge pull request #1319 from gsd-build/fix/enforce-worktree-isolation-agents

fix: enforce worktree isolation for code-writing agents

get-shit-done/workflows/diagnose-issues.md

@@ -81,6 +81,7 @@ For each gap, fill the debug-subagent-prompt template and spawn:
 Task(
   prompt=filled_debug_subagent_prompt + "\n\n<files_to_read>\n- {phase_dir}/{phase_num}-UAT.md\n- .planning/STATE.md\n</files_to_read>",
   subagent_type="gsd-debugger",
+  isolation="worktree",
   description="Debug: {truth_short}"
 )
 ```

get-shit-done/workflows/execute-phase.md

@@ -14,8 +14,8 @@ Orchestrator coordinates, not executes. Each subagent loads the full execute-pla
   instead of spawning parallel agents. Only attempt parallel spawning if the user
   explicitly requests it — and in that case, rely on the spot-check fallback in step 3
   to detect completion.
-- **Other runtimes (Gemini, Codex, OpenCode):** If Task/subagent API is unavailable, use sequential
-  inline execution as the fallback.
+- **Other runtimes:** If `Task`/`task` tool is unavailable, use sequential inline execution as the
+  fallback. Check for tool availability at runtime rather than assuming based on runtime name.
 
 **Fallback rule:** If a spawned agent completes its work (commits visible, SUMMARY.md exists) but
 the orchestrator never receives the completion signal, treat it as successful based on spot-checks
@@ -226,6 +226,7 @@ Execute each selected wave in sequence. Within a wave: parallel if `PARALLELIZAT
    Task(
      subagent_type="gsd-executor",
      model="{executor_model}",
+     isolation="worktree",
      prompt="
        <objective>
        Execute plan {plan_number} of phase {phase_number}-{phase_name}.

get-shit-done/workflows/execute-plan.md

@@ -67,7 +67,7 @@ grep -n "type=\"checkpoint" .planning/phases/XX-name/{phase}-{plan}-PLAN.md
 | Verify-only | B (segmented) | Segments between checkpoints. After none/human-verify → SUBAGENT. After decision/human-action → MAIN |
 | Decision | C (main) | Execute entirely in main context |
 
-**Pattern A:** init_agent_tracking → spawn Task(subagent_type="gsd-executor", model=executor_model) with prompt: execute plan at [path], autonomous, all tasks + SUMMARY + commit, follow deviation/auth rules, report: plan name, tasks, SUMMARY path, commit hash → track agent_id → wait → update tracking → report.
+**Pattern A:** init_agent_tracking → spawn Task(subagent_type="gsd-executor", model=executor_model, isolation="worktree") with prompt: execute plan at [path], autonomous, all tasks + SUMMARY + commit, follow deviation/auth rules, report: plan name, tasks, SUMMARY path, commit hash → track agent_id → wait → update tracking → report.
 
 **Pattern B:** Execute segment-by-segment. Autonomous segments: spawn subagent for assigned tasks only (no SUMMARY/commit). Checkpoints: main context. After all segments: aggregate, create SUMMARY, commit. See segment_execution.
 

get-shit-done/workflows/quick.md

@@ -536,6 +536,7 @@ Execute quick task ${quick_id}.
 ",
   subagent_type="gsd-executor",
   model="{executor_model}",
+  isolation="worktree",
   description="Execute: ${DESCRIPTION}"
 )
 ```