prizmkit 1.1.68 → 1.1.69

package/bundled/VERSION.json

@@ -1,5 +1,5 @@
 {
-  "frameworkVersion": "1.1.68",
-  "bundledAt": "2026-06-09T14:36:58.835Z",
-  "bundledFrom": "82060fd"
+  "frameworkVersion": "1.1.69",
+  "bundledAt": "2026-06-09T23:54:02.566Z",
+  "bundledFrom": "7453dba"
 }

package/bundled/dev-pipeline/lib/heartbeat.sh

@@ -90,8 +90,8 @@ PY
             fi
             prev_child_activity_signature="$child_activity_signature"
 
-            # Track progress staleness. A Codex parent can sit in `wait`
-            # while child transcripts keep growing, so child activity counts.
+            # Track progress staleness. Parent sessions can sit in a wait/polling
+            # tool while child transcripts keep growing, so child activity counts.
             if [[ $growth -eq 0 && $child_growth -eq 0 ]]; then
                 stale_seconds=$((stale_seconds + heartbeat_interval))
             else
@@ -174,9 +174,9 @@ PY
             fi
 
             # Stale-kill: auto-terminate process if no progress for too long.
-            # Codex parent sessions can sit on the `wait` tool while a spawned
-            # subagent is still doing useful work. Give that valid wait a longer
-            # stale window; normal single-agent stalls still use the base limit.
+            # Parent sessions can wait on spawned work; child transcript growth
+            # counts as progress above, while silent waits still use the active
+            # stale window to surface stuck agents promptly.
             if [[ $effective_stale_kill_threshold -gt 0 && $stale_seconds -ge $effective_stale_kill_threshold ]]; then
                 local stale_mins=$((stale_seconds / 60))
                 echo -e "  ${RED}[HEARTBEAT]${NC} ${mins}m${secs}s | log: ${size_display} | ${RED}STALE-KILL: no progress for ${stale_mins}m (threshold: ${effective_stale_kill_threshold}s)${NC}"

package/bundled/dev-pipeline/scripts/parse-stream-progress.py

@@ -63,7 +63,8 @@ PHASE_KEYWORDS = {
 class ProgressTracker:
     """Tracks progress state from stream-json events."""
 
-    def __init__(self):
+    def __init__(self, session_log=None):
+        self.session_log_path = Path(session_log).expanduser() if session_log else None
         self.message_count = 0
         self.current_tool = None
         self.current_tool_input_summary = ""
@@ -78,12 +79,19 @@ class ProgressTracker:
         self.active_subagent_count = 0
         self.subagent_status_counts = Counter()
         self.codex_child_thread_ids = set()
+        self.claude_session_id = ""
+        self.claude_cwd = ""
+        self.claude_task_states = {}
         self.child_session_files = []
         self.child_total_bytes = 0
         self.child_activity_signature = ""
         self.last_child_activity_at = ""
         self._codex_child_session_paths = {}
+        self._claude_child_session_files = []
         self._last_child_scan_at = 0.0
+        self._last_claude_fallback_scan_at = 0.0
+        self._last_claude_fallback_scan_key = ""
+        self._claude_fallback_scan_interval_seconds = 10.0
         self._text_buffer = ""
         self._in_tool_use = False
         self._current_tool_input_parts = []
@@ -195,11 +203,76 @@ class ProgressTracker:
             self.is_active = True
 
         elif event_type == "system":
-            # System events (hooks, init, etc.) — track but don't count as messages
+            # System events (hooks, init, task notifications, etc.) — track but don't count as messages.
             self.event_format = self.event_format or "stream-json"
             subtype = event.get("subtype", "")
             if subtype == "init":
                 self.is_active = True
+                session_id = event.get("session_id")
+                if isinstance(session_id, str) and session_id.strip():
+                    self.claude_session_id = session_id.strip()
+                cwd = event.get("cwd")
+                if isinstance(cwd, str) and cwd.strip():
+                    self.claude_cwd = cwd.strip()
+            elif subtype == "task_started":
+                task_id = event.get("task_id")
+                if isinstance(task_id, str) and task_id.strip():
+                    self.claude_task_states[task_id.strip()] = {
+                        "status": "running",
+                        "summary": str(event.get("description") or "")[:120],
+                        "tool_use_id": str(event.get("tool_use_id") or ""),
+                        "task_type": str(event.get("task_type") or ""),
+                        "subagent_type": str(event.get("subagent_type") or ""),
+                    }
+                    self._update_claude_subagent_status_counts()
+            elif subtype in ("task_updated", "task_progress"):
+                task_id = event.get("task_id")
+                if isinstance(task_id, str) and task_id.strip():
+                    state = self.claude_task_states.setdefault(task_id.strip(), {})
+                    patch = event.get("patch") if isinstance(event.get("patch"), dict) else {}
+                    status = patch.get("status") or event.get("status")
+                    if status:
+                        state["status"] = str(status)
+                    summary = patch.get("summary") or patch.get("description") or event.get("summary") or event.get("description")
+                    if summary:
+                        state["summary"] = str(summary)[:120]
+                    else:
+                        state.setdefault("summary", "")
+                    tool_use_id = patch.get("tool_use_id") or event.get("tool_use_id")
+                    if tool_use_id:
+                        state["tool_use_id"] = str(tool_use_id)
+                    else:
+                        state.setdefault("tool_use_id", "")
+                    task_type = patch.get("task_type") or event.get("task_type")
+                    if task_type:
+                        state["task_type"] = str(task_type)
+                    else:
+                        state.setdefault("task_type", "")
+                    subagent_type = patch.get("subagent_type") or event.get("subagent_type")
+                    if subagent_type:
+                        state["subagent_type"] = str(subagent_type)
+                    else:
+                        state.setdefault("subagent_type", "")
+                    self._update_claude_subagent_status_counts()
+            elif subtype == "task_notification":
+                task_id = event.get("task_id")
+                if isinstance(task_id, str) and task_id.strip():
+                    state = self.claude_task_states.setdefault(task_id.strip(), {})
+                    status = event.get("status") or "completed"
+                    state["status"] = str(status)
+                    state["summary"] = str(event.get("summary") or state.get("summary") or "")[:120]
+                    state.setdefault("tool_use_id", str(event.get("tool_use_id") or ""))
+                    task_type = event.get("task_type")
+                    if task_type:
+                        state["task_type"] = str(task_type)
+                    else:
+                        state.setdefault("task_type", "")
+                    subagent_type = event.get("subagent_type")
+                    if subagent_type:
+                        state["subagent_type"] = str(subagent_type)
+                    else:
+                        state.setdefault("subagent_type", "")
+                    self._update_claude_subagent_status_counts()
 
         # ── Claude API raw stream format ────────────────────────────
         elif event_type == "message_start":
@@ -391,16 +464,135 @@ class ProgressTracker:
             pass
         return str(matches[0])
 
+    def _is_tracked_claude_subagent_state(self, state):
+        """Return true for Claude Code task events representing in-process agents."""
+        if not isinstance(state, dict):
+            return False
+        task_type = str(state.get("task_type") or "")
+        task_type_lower = task_type.lower()
+        subagent_type = str(state.get("subagent_type") or "")
+        if task_type_lower == "local_bash":
+            return False
+        tracked_types = {"in_process_teammate", "subagent", "agent", "teammate"}
+        if task_type_lower in tracked_types:
+            return True
+        if task_type_lower == "local_agent" and subagent_type:
+            return True
+        summary = str(state.get("summary") or "")
+        return bool(
+            not task_type
+            and summary.lower().startswith(("dev:", "critic:", "reviewer:", "agent:"))
+        )
+
+    def _has_tracked_claude_subagent_task(self):
+        """Return true once a Claude Code local-agent/subagent task has been observed."""
+        return any(
+            self._is_tracked_claude_subagent_state(state)
+            for state in self.claude_task_states.values()
+        )
+
+    def _update_claude_subagent_status_counts(self):
+        """Track Claude Code in-process teammate task state counts."""
+        counts = Counter()
+        active = 0
+        inactive_statuses = {
+            "completed",
+            "failed",
+            "cancelled",
+            "canceled",
+            "killed",
+            "stopped",
+            "success",
+            "error",
+        }
+        for state in self.claude_task_states.values():
+            if not self._is_tracked_claude_subagent_state(state):
+                continue
+            status = str(state.get("status") or "unknown")
+            counts[status] += 1
+            if status.lower() not in inactive_statuses:
+                active += 1
+            summary = state.get("summary") or state.get("subagent_type")
+            if summary:
+                self.last_text_snippet = str(summary).strip()[:120]
+                self._detect_phase(str(summary))
+        self.subagent_status_counts = counts
+        self.active_subagent_count = active
+
+    def _claude_projects_dir(self):
+        """Return the Claude Code projects directory for transcript lookup."""
+        projects_dir = os.environ.get("CLAUDE_PROJECTS_DIR")
+        if projects_dir:
+            return Path(projects_dir).expanduser()
+        claude_config_dir = os.environ.get("CLAUDE_CONFIG_DIR")
+        if claude_config_dir:
+            return Path(claude_config_dir).expanduser() / "projects"
+        claude_home = os.environ.get("CLAUDE_HOME")
+        if claude_home:
+            return Path(claude_home).expanduser() / "projects"
+        return Path.home() / ".claude" / "projects"
+
+    def _claude_project_key(self):
+        """Encode cwd the same way Claude Code stores project transcript dirs."""
+        cwd = self.claude_cwd
+        if not cwd:
+            return ""
+        return cwd.replace("\\", "-").replace("/", "-").replace(":", "")
+
+    def _find_claude_child_session_files(self):
+        """Find Claude Code subagent transcripts for this parent session."""
+        if not self.claude_session_id:
+            return []
+
+        projects_dir = self._claude_projects_dir()
+        if not projects_dir.exists():
+            return []
+
+        candidates = []
+        project_key = self._claude_project_key()
+        if project_key:
+            candidates.append(
+                projects_dir / project_key / self.claude_session_id / "subagents"
+            )
+
+        for candidate in candidates:
+            if candidate.exists():
+                try:
+                    return sorted(candidate.glob("*.jsonl"))
+                except OSError:
+                    return []
+
+        # Fallback for non-standard cwd encoding or custom Claude homes. Avoid
+        # repeatedly walking every stored transcript before any Agent task exists.
+        if not self._has_tracked_claude_subagent_task():
+            return []
+
+        fallback_scan_key = f"{projects_dir}:{self.claude_session_id}"
+        now = time.monotonic()
+        if (
+            self._last_claude_fallback_scan_key == fallback_scan_key
+            and now - self._last_claude_fallback_scan_at < self._claude_fallback_scan_interval_seconds
+        ):
+            return self._claude_child_session_files
+        self._last_claude_fallback_scan_key = fallback_scan_key
+        self._last_claude_fallback_scan_at = now
+        try:
+            matches = sorted(projects_dir.rglob(f"{self.claude_session_id}/subagents/*.jsonl"))
+        except OSError:
+            return []
+        return matches
+
     def refresh_child_session_activity(self, force=False):
-        """Refresh Codex child transcript file stats.
+        """Refresh child transcript file stats.
 
         The heartbeat monitor uses this activity signature to treat subagent
-        transcript growth as real progress while the parent Codex session is
-        blocked in `wait`.
+        transcript growth as real progress while the parent session is blocked
+        waiting for a child agent/tool result. Supports Codex child threads and
+        Claude Code in-process teammate transcripts.
         """
         previous_signature = self.child_activity_signature
 
-        if not self.codex_child_thread_ids:
+        if not self.codex_child_thread_ids and not self.claude_session_id:
             self.child_session_files = []
             self.child_total_bytes = 0
             self.child_activity_signature = ""
@@ -420,6 +612,7 @@ class ProgressTracker:
                     found = self._find_codex_child_session_file(thread_id)
                     if found:
                         self._codex_child_session_paths[thread_id] = found
+            self._claude_child_session_files = self._find_claude_child_session_files()
             self._last_child_scan_at = now
 
         files = []
@@ -427,24 +620,22 @@ class ProgressTracker:
         total_bytes = 0
         max_mtime = 0.0
 
-        for thread_id in sorted(self.codex_child_thread_ids):
-            path = self._codex_child_session_paths.get(thread_id)
-            if not path:
-                continue
+        def add_file(kind, identifier, path):
+            nonlocal total_bytes, max_mtime
             try:
                 stat = os.stat(path)
             except OSError:
-                continue
-
+                return
+            path_str = str(path)
             total_bytes += stat.st_size
             max_mtime = max(max_mtime, stat.st_mtime)
-            signature_parts.append(
-                f"{thread_id}:{stat.st_size}:{getattr(stat, 'st_mtime_ns', int(stat.st_mtime * 1_000_000_000))}"
-            )
+            mtime_ns = getattr(stat, "st_mtime_ns", int(stat.st_mtime * 1_000_000_000))
+            signature_parts.append(f"{kind}:{identifier}:{stat.st_size}:{mtime_ns}")
             files.append(
                 {
-                    "thread_id": thread_id,
-                    "path": path,
+                    "kind": kind,
+                    "thread_id": identifier,
+                    "path": path_str,
                     "size": stat.st_size,
                     "mtime": datetime.fromtimestamp(
                         stat.st_mtime, timezone.utc
@@ -452,6 +643,14 @@ class ProgressTracker:
                 }
             )
 
+        for thread_id in sorted(self.codex_child_thread_ids):
+            path = self._codex_child_session_paths.get(thread_id)
+            if path:
+                add_file("codex", thread_id, path)
+
+        for path in self._claude_child_session_files:
+            add_file("claude", path.stem, path)
+
         self.child_session_files = files
         self.child_total_bytes = total_bytes
         self.child_activity_signature = "|".join(signature_parts)
@@ -519,7 +718,7 @@ def atomic_write_json(data, filepath):
 
 def tail_and_parse(session_log, progress_file, poll_interval=0.5):
     """Tail session log and parse stream-json events."""
-    tracker = ProgressTracker()
+    tracker = ProgressTracker(session_log)
     last_write_state = None
 
     def state_key(state):

package/bundled/dev-pipeline/templates/bootstrap-tier2.md

@@ -14,6 +14,12 @@ You are the **session orchestrator**. Implement Feature {{FEATURE_ID}}: "{{FEATU
 
 **Tier 2 — Dual Agent**: You handle context + planning directly. Then spawn Dev and Reviewer subagents. Spawn Dev and Reviewer agents via the Agent tool.
 
+**Agent spawn failure policy (all Agent tool calls)**:
+- If spawning Dev, Reviewer, or Critic fails with team/config/lock errors, retry at most once.
+- If the second attempt fails, do not keep spawning variants and do not enter artifact polling for Implementation Log, challenge report, or review report markers.
+- Use the documented inline/recovery fallback for that phase: write the required report yourself where possible, complete remaining Dev work directly in the orchestrator when safe, or write `failure-log.md` with the spawn error and last observable state before stopping for recovery.
+- Apply the same cap to any re-spawn for report repair or resume prompts; do not burn multiple minutes on identical team/config/lock failures.
+
 ### Feature Description
 
 {{FEATURE_DESCRIPTION}}
@@ -163,6 +169,8 @@ Before proceeding past CP-1, verify:
 
 Spawn Reviewer agent (Agent tool, subagent_type="prizm-dev-team-reviewer", mode="plan", run_in_background=false).
 
+Spawn failure cap: for team/config/lock errors, retry at most once for this Reviewer spawn. If the second attempt fails, do not poll for report artifacts; fix/check the plan inline or write `failure-log.md` before stopping for recovery.
+
 Prompt:
 > "Read {{REVIEWER_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
 > 1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST — Section 3 has project context, Section 4 has file manifest.
@@ -186,6 +194,8 @@ If CRITIC:MISSING — skip Phase 3.5 entirely and proceed to Phase 4. Log: "Crit
 
 Spawn Critic agent (Agent tool, subagent_type="prizm-dev-team-critic", mode="plan", run_in_background=false).
 
+Spawn failure cap: for team/config/lock errors, retry at most once for this Critic spawn. If the second attempt fails, do not poll for `challenge-report.md`; perform the plan challenge inline and record the fallback.
+
 Prompt:
 > "Read {{CRITIC_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
 > **MODE: Plan Challenge**
@@ -208,6 +218,8 @@ Wait for Critic to return.
 
 Spawn Dev subagent (Agent tool, subagent_type="prizm-dev-team-dev", run_in_background=false).
 
+Spawn failure cap: for team/config/lock errors, retry at most once for this Dev spawn. If the second attempt fails, do not poll for `## Implementation Log`; write `failure-log.md` and either implement remaining tasks directly in the orchestrator or stop for recovery.
+
 Prompt:
 > "Read {{DEV_SUBAGENT_PATH}}. Implement feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}).
 > **IMPORTANT**: Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST — Section 3 has Prizm Context (TRAPS/RULES), Section 4 has File Manifest with paths and interfaces.
@@ -232,6 +244,8 @@ If GATE:MISSING — send message to Dev (re-spawn if needed): "Write the '## Imp
 
 Spawn Reviewer subagent (Agent tool, subagent_type="prizm-dev-team-reviewer", run_in_background=false).
 
+Spawn failure cap: for team/config/lock errors, retry at most once for this Reviewer spawn. If the second attempt fails, do not poll for `review-report.md`; write `failure-log.md` with the spawn error and last observable state before stopping or performing an inline fallback.
+
 Prompt:
 > "Read {{REVIEWER_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
 > 1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/spec.md` for goals and acceptance criteria
@@ -248,7 +262,11 @@ After Reviewer agent returns, verify the review report was written:
 ```bash
 grep -q "## Verdict" .prizmkit/specs/{{FEATURE_SLUG}}/review-report.md && echo "GATE:PASS" || echo "GATE:MISSING"
 ```
-If GATE:MISSING — send message to Reviewer (re-spawn if needed): "Write review-report.md to .prizmkit/specs/{{FEATURE_SLUG}}/."
+If GATE:MISSING:
+- Do not re-spawn Reviewer or re-run `/prizmkit-code-review` in an unbounded report-repair loop.
+- Perform one bounded status check; retry at most once: inspect Reviewer output, code-review skill output, `review-report.md` path, and any Reviewer/Dev spawn messages.
+- If the missing report is caused by team/config/lock errors from Reviewer or the internal code-review loop, write `failure-log.md` with the spawn/skill error and last observable state.
+- If the report is still missing after that single check/retry, either perform a safe inline fallback review and write `review-report.md` with `## Verdict`, or stop with a clear recovery failure.
 
 Read `review-report.md` and check the Verdict:
 - `PASS` → proceed to next phase

package/bundled/dev-pipeline/templates/bootstrap-tier3.md

@@ -14,6 +14,12 @@ You are the **session orchestrator**. Implement Feature {{FEATURE_ID}}: "{{FEATU
 
 **Tier 3 — Full Team**: For complex features, use the full pipeline (Phase 0–6) with Dev + Reviewer agents spawned via the Agent tool.
 
+**Agent spawn failure policy (all Agent tool calls)**:
+- If spawning Dev, Reviewer, or Critic fails with team/config/lock errors, retry at most once.
+- If the second attempt fails, do not keep spawning variants and do not enter artifact polling for Implementation Log, challenge report, or review report markers.
+- Use the documented inline/recovery fallback for that phase: write the required report yourself where possible, complete remaining Dev work directly in the orchestrator when safe, or write `failure-log.md` with the spawn error and last observable state before stopping for recovery.
+- Apply the same cap to any re-spawn for report repair or resume prompts; do not burn multiple minutes on identical team/config/lock failures.
+
 ### Feature Description
 
 {{FEATURE_DESCRIPTION}}
@@ -190,6 +196,8 @@ Before proceeding past CP-1, verify:
 
 Spawn Reviewer agent (Agent tool, subagent_type="prizm-dev-team-reviewer", mode="plan", run_in_background=false).
 
+Spawn failure cap: for team/config/lock errors, retry at most once for this Reviewer spawn. If the second attempt fails, do not poll for report artifacts; fix/check the plan inline or write `failure-log.md` before stopping for recovery.
+
 Prompt:
 > "Read {{REVIEWER_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
 > 1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST — Section 3 has project context, Section 4 has file manifest.
@@ -217,6 +225,8 @@ If CRITIC:MISSING — skip Phase 3.5 entirely and proceed to Phase 4. Log: "Crit
 
 Spawn Critic agent (Agent tool, subagent_type="prizm-dev-team-critic", mode="plan", run_in_background=false).
 
+Spawn failure cap: for team/config/lock errors, retry at most once for this Critic spawn. If the second attempt fails, do not poll for challenge reports; perform the plan challenge inline and record the fallback.
+
 Prompt:
 > "Read {{CRITIC_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
 > **MODE: Plan Challenge**
@@ -263,6 +273,8 @@ grep -c '^\- \[ \]' .prizmkit/specs/{{FEATURE_SLUG}}/plan.md 2>/dev/null || true
 
 Spawn Dev agent (Agent tool, subagent_type="prizm-dev-team-dev", run_in_background=false).
 
+Spawn failure cap: for team/config/lock errors, retry at most once for this Dev spawn. If the second attempt fails, do not poll for `## Implementation Log`; write `failure-log.md` and either implement remaining tasks directly in the orchestrator or stop for recovery.
+
 Prompt:
 > "Read {{DEV_SUBAGENT_PATH}}. Implement feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}).
 > **IMPORTANT**: Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST — Section 3 has Prizm Context (TRAPS/RULES), Section 4 has File Manifest with paths and interfaces.
@@ -297,6 +309,8 @@ All tasks `[x]`, tests pass.
 
 Spawn Reviewer agent (Agent tool, subagent_type="prizm-dev-team-reviewer", run_in_background=false).
 
+Spawn failure cap: for team/config/lock errors, retry at most once for this Reviewer spawn. If the second attempt fails, do not poll for `review-report.md`; write `failure-log.md` with the spawn error and last observable state before stopping or performing an inline fallback.
+
 Prompt:
 > "Read {{REVIEWER_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
 > 1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/spec.md` for goals and acceptance criteria
@@ -313,7 +327,11 @@ After Reviewer agent returns, verify the review report was written:
 ```bash
 grep -q "## Verdict" .prizmkit/specs/{{FEATURE_SLUG}}/review-report.md && echo "GATE:PASS" || echo "GATE:MISSING"
 ```
-If GATE:MISSING — send message to Reviewer (re-spawn if needed): "Write review-report.md to .prizmkit/specs/{{FEATURE_SLUG}}/."
+If GATE:MISSING:
+- Do not re-spawn Reviewer or re-run `/prizmkit-code-review` in an unbounded report-repair loop.
+- Perform one bounded status check; retry at most once: inspect Reviewer output, code-review skill output, `review-report.md` path, and any Reviewer/Dev spawn messages.
+- If the missing report is caused by team/config/lock errors from Reviewer or the internal code-review loop, write `failure-log.md` with the spawn/skill error and last observable state.
+- If the report is still missing after that single check/retry, either perform a safe inline fallback review and write `review-report.md` with `## Verdict`, or stop with a clear recovery failure.
 
 Read `review-report.md` and check the Verdict:
 - `PASS` → proceed to next phase

package/bundled/dev-pipeline/templates/refactor-bootstrap-prompt.md

@@ -80,6 +80,12 @@ You are the **refactor session orchestrator**. Execute Refactor {{REFACTOR_ID}}:
 
 **YOU are the orchestrator. Execute each phase by spawning the appropriate team agent with run_in_background=false.**
 
+**Agent spawn failure policy (all Agent tool calls)**:
+- If spawning Dev or Reviewer fails with team/config/lock errors, retry at most once.
+- If the second attempt fails, do not keep spawning variants and do not enter artifact polling for Implementation Log, review-report, or refactor-report markers.
+- Use the documented inline/recovery fallback for that phase: complete remaining refactor work directly in the orchestrator when safe, write the required report yourself where possible, or write `failure-log.md` with the spawn error and last observable state before stopping for recovery.
+- Apply the same cap to any re-spawn for report repair or resume prompts; do not burn multiple minutes on identical team/config/lock failures.
+
 ## Workflow Checkpoint System
 
 A checkpoint file tracks your progress through this workflow:
@@ -164,6 +170,7 @@ Include browser verification approach in plan.md:
 **Goal**: Execute all tasks from plan.md while preserving existing behavior.
 
 - Spawn Dev agent (Agent tool, subagent_type="prizm-dev-team-dev", run_in_background=false)
+  Spawn failure cap: for team/config/lock errors, retry at most once for this Dev spawn. If the second attempt fails, do not poll for `## Implementation Log`; write `failure-log.md` and either complete remaining refactor work directly in the orchestrator or stop for recovery.
   Prompt: "Read {{DEV_SUBAGENT_PATH}}. For refactor {{REFACTOR_ID}} ('{{REFACTOR_TITLE}}'):
   1. Read `.prizmkit/refactor/{{REFACTOR_ID}}/spec.md` and `.prizmkit/refactor/{{REFACTOR_ID}}/plan.md`
   2. Read `.prizmkit/prizm-docs/` for affected modules (TRAPS, RULES, PATTERNS)
@@ -201,6 +208,7 @@ Include browser verification approach in plan.md:
 **Goal**: Verify refactoring quality and behavior preservation.
 
 - Spawn Reviewer agent (Agent tool, subagent_type="prizm-dev-team-reviewer", run_in_background=false)
+  Spawn failure cap: for team/config/lock errors, retry at most once for this Reviewer spawn. If the second attempt fails, do not poll for `review-report.md`; write `failure-log.md` with the spawn error and last observable state before stopping or performing an inline fallback.
   Prompt: "Read {{REVIEWER_SUBAGENT_PATH}}. For refactor {{REFACTOR_ID}}:
   1. Read `.prizmkit/refactor/{{REFACTOR_ID}}/spec.md` for goals and behavior preservation contracts
   2. Read `.prizmkit/refactor/{{REFACTOR_ID}}/plan.md` for architecture decisions and completed tasks
@@ -221,7 +229,20 @@ Include browser verification approach in plan.md:
   7. Report: verdict (PASS/NEEDS_FIXES), number of rounds, findings fixed/rejected
   "
 - **Wait for Reviewer to return**
-- Read `review-report.md` — if PASS proceed, if NEEDS_FIXES log remaining findings and proceed.
+- **Gate Check — Review Report**:
+  After Reviewer returns, verify the review report contains a verdict:
+  ```bash
+  grep -q "## Verdict" .prizmkit/refactor/{{REFACTOR_ID}}/review-report.md && echo "GATE:PASS" || echo "GATE:MISSING"
+  ```
+  If GATE:MISSING:
+  - Do not enter an unbounded report-repair loop and do not repeatedly re-spawn Reviewer.
+  - Perform one bounded status check; retry at most once: inspect the Reviewer output, `review-report.md` path, and any internal Reviewer/Dev spawn messages from `/prizmkit-code-review`.
+  - If the missing report is caused by team/config/lock errors from the Reviewer or internal Reviewer/Dev agent spawn, retry the Reviewer agent at most once only if it appears transient.
+  - If the report is still missing after that single check/retry, write `.prizmkit/refactor/{{REFACTOR_ID}}/failure-log.md` with the spawn/skill error and last observable state, then either perform a safe inline fallback review (spec/plan/diff/tests → write `review-report.md` with `## Verdict`) or stop with a clear recovery failure.
+
+Read `review-report.md` and check the Verdict:
+- `PASS` → proceed to next phase
+- `NEEDS_FIXES` → log remaining findings and proceed (do not retry externally)
 - **CP-RF-3**: Code review complete, tests pass, behavior preserved
 - **Checkpoint update**: set step `prizmkit-code-review` to `"completed"` in `{{CHECKPOINT_PATH}}`
 

package/bundled/dev-pipeline/templates/sections/phase-critic-plan-full.md

@@ -8,6 +8,16 @@ If CRITIC:MISSING — skip this phase entirely and proceed. Log: "Critic agent n
 
 **Choose ONE path based on `{{CRITIC_COUNT}}`:**
 
+**Agent spawn failure policy**:
+- If spawning Critic fails with team/config/lock errors, retry at most once.
+- If the second attempt fails, do not keep spawning variants. Either create the required team once (when team tooling is available) or perform the plan challenge inline and write the required challenge report yourself.
+- Record the fallback in the report; do not burn multiple minutes on repeated identical spawn failures.
+
+**No silent report polling**:
+- Do NOT run a long no-output loop waiting for `challenge-report*.md`.
+- If you need to wait for a report file, use a short bounded check (≤120s) that prints elapsed time and reports present on every iteration.
+- If reports are still missing after the bounded check, request one status update; if still missing, perform the missing challenge lens inline and continue.
+
 **If {{CRITIC_COUNT}} = 1 → Single Critic** (skip to CP-2.5 after this):
 
 **Spawn Agent**:

package/bundled/dev-pipeline/templates/sections/phase-critic-plan.md

@@ -16,6 +16,16 @@ If CRITIC:MISSING — skip this phase entirely and proceed. Log: "Critic agent n
 **Prompt**:
 > {{AGENT_PROMPT_CRITIC_PLAN_CHALLENGE}}
 
+**Agent spawn failure policy**:
+- If spawning Critic fails with team/config/lock errors, retry at most once.
+- If the second attempt fails, do not keep spawning variants. Either create the required team once (when team tooling is available) or perform the plan challenge inline and write `challenge-report.md` yourself.
+- Record the fallback in the report; do not burn multiple minutes on repeated identical spawn failures.
+
+**No silent report polling**:
+- Do NOT run a long no-output loop waiting for `challenge-report.md`.
+- If you need to wait for the report file, use a short bounded check (≤120s) that prints elapsed time and whether the report exists on every iteration.
+- If the report is still missing after the bounded check, request one status update; if still missing, perform the challenge inline and continue.
+
 Wait for Critic to return.
 - Read challenge-report.md. For items marked CRITICAL/HIGH: decide whether to adjust plan.md or document why the plan stands.
 - Max 1 plan revision round.

package/bundled/dev-pipeline/templates/sections/phase-implement-agent.md

@@ -15,11 +15,23 @@
 | subagent_type | prizm-dev-team-dev |
 | run_in_background | false |
 
+**Agent spawn failure policy**:
+- If spawning Dev fails with team/config/lock errors, retry at most once.
+- If the second attempt fails, do not enter Implementation Log polling or repeated recovery spawn loops.
+- Use the documented inline/recovery fallback: write `failure-log.md` with the spawn error and last observable state, then either complete remaining tasks directly in the orchestrator or stop with a clear failure for recovery.
+- Apply the same cap to Dev re-spawns for Implementation Log repair or resume prompts; do not burn multiple minutes on identical team/config/lock failures.
+
 **Prompt**:
 > {{AGENT_PROMPT_DEV_IMPLEMENT}}
 
 Wait for Dev to return. All tasks must be `[x]`, tests pass.
 
+**No silent artifact polling**:
+- Do NOT run a long no-output loop that only waits for `## Implementation Log` or any other file marker.
+- If you must wait for Dev after spawning or sending a status request, use short bounded checks (≤120s) that print a heartbeat line each iteration with: elapsed time, remaining unchecked task count, whether `## Implementation Log` exists, and whether `git diff --stat` changed.
+- If Dev has no transcript/file/diff progress for one bounded check, send one status request. If there is still no progress on the next bounded check, stop waiting, write `failure-log.md` with the last observable state, and follow Subagent Timeout Recovery.
+- Prefer the Agent tool's completion notification or Dev's `COMPLETION_SIGNAL`; file presence alone is not a liveness signal.
+
 **Gate Check — Implementation Log**:
 After Dev agent returns, verify the Implementation Log was written:
 ```bash

package/bundled/dev-pipeline/templates/sections/phase-implement-full.md

@@ -22,9 +22,21 @@ grep -c '^\- \[ \]' .prizmkit/specs/{{FEATURE_SLUG}}/plan.md 2>/dev/null || true
 | subagent_type | prizm-dev-team-dev |
 | run_in_background | false |
 
+**Agent spawn failure policy**:
+- If spawning Dev fails with team/config/lock errors, retry at most once.
+- If the second attempt fails, do not enter Implementation Log polling or repeated recovery spawn loops.
+- Use the documented inline/recovery fallback: write `failure-log.md` with the spawn error and last observable state, then either complete remaining tasks directly in the orchestrator or stop with a clear failure for recovery.
+- Apply the same cap to Dev re-spawns for Implementation Log repair or resume prompts; do not burn multiple minutes on identical team/config/lock failures.
+
 **Prompt**:
 > {{AGENT_PROMPT_DEV_IMPLEMENT}}
 
+**No silent artifact polling**:
+- Do NOT run a long no-output loop that only waits for `## Implementation Log` or any other file marker.
+- If you must wait for Dev after spawning or sending a status request, use short bounded checks (≤120s) that print a heartbeat line each iteration with: elapsed time, remaining unchecked task count, whether `## Implementation Log` exists, and whether `git diff --stat` changed.
+- If Dev has no transcript/file/diff progress for one bounded check, send one status request. If there is still no progress on the next bounded check, stop waiting, write `failure-log.md` with the last observable state, and follow Subagent Timeout Recovery.
+- Prefer the Agent tool's completion notification or Dev's `COMPLETION_SIGNAL`; file presence alone is not a liveness signal.
+
 **Gate Check — Implementation Log**:
 After Dev agent returns, verify the Implementation Log was written:
 ```bash

package/bundled/dev-pipeline/templates/sections/phase-review-agent.md

@@ -9,7 +9,11 @@ After `/prizmkit-code-review` returns, verify the review report:
 ```bash
 grep -q "## Verdict" .prizmkit/specs/{{FEATURE_SLUG}}/review-report.md && echo "GATE:PASS" || echo "GATE:MISSING"
 ```
-If GATE:MISSING — re-run `/prizmkit-code-review`.
+If GATE:MISSING:
+- Do not re-run `/prizmkit-code-review` in an unbounded report-repair loop.
+- Perform one bounded status check; retry at most once: inspect the skill output, `review-report.md` path, and any Reviewer/Dev spawn messages.
+- If the missing report is caused by team/config/lock errors from the internal Reviewer/Dev agent spawn, retry `/prizmkit-code-review` at most once only if it appears transient.
+- If the report is still missing after that single check/retry, write `failure-log.md` with the spawn/skill error and last observable state, then either perform a safe inline fallback review (spec/plan/diff/tests → write `review-report.md` with `## Verdict`) or stop with a clear recovery failure.
 
 Read `review-report.md` and check the Verdict:
 - `PASS` → proceed to next phase

package/bundled/dev-pipeline/templates/sections/phase-review-full.md

@@ -9,7 +9,11 @@ After `/prizmkit-code-review` returns, verify the review report:
 ```bash
 grep -q "## Verdict" .prizmkit/specs/{{FEATURE_SLUG}}/review-report.md && echo "GATE:PASS" || echo "GATE:MISSING"
 ```
-If GATE:MISSING — re-run `/prizmkit-code-review`.
+If GATE:MISSING:
+- Do not re-run `/prizmkit-code-review` in an unbounded report-repair loop.
+- Perform one bounded status check; retry at most once: inspect the skill output, `review-report.md` path, and any Reviewer/Dev spawn messages.
+- If the missing report is caused by team/config/lock errors from the internal Reviewer/Dev agent spawn, retry `/prizmkit-code-review` at most once only if it appears transient.
+- If the report is still missing after that single check/retry, write `failure-log.md` with the spawn/skill error and last observable state, then either perform a safe inline fallback review (spec/plan/diff/tests → write `review-report.md` with `## Verdict`) or stop with a clear recovery failure.
 
 Read `review-report.md` and check the Verdict:
 - `PASS` → proceed to next phase

package/bundled/dev-pipeline-windows/scripts/parse-stream-progress.py

@@ -63,7 +63,8 @@ PHASE_KEYWORDS = {
 class ProgressTracker:
     """Tracks progress state from stream-json events."""
 
-    def __init__(self):
+    def __init__(self, session_log=None):
+        self.session_log_path = Path(session_log).expanduser() if session_log else None
         self.message_count = 0
         self.current_tool = None
         self.current_tool_input_summary = ""
@@ -78,12 +79,19 @@ class ProgressTracker:
         self.active_subagent_count = 0
         self.subagent_status_counts = Counter()
         self.codex_child_thread_ids = set()
+        self.claude_session_id = ""
+        self.claude_cwd = ""
+        self.claude_task_states = {}
         self.child_session_files = []
         self.child_total_bytes = 0
         self.child_activity_signature = ""
         self.last_child_activity_at = ""
         self._codex_child_session_paths = {}
+        self._claude_child_session_files = []
         self._last_child_scan_at = 0.0
+        self._last_claude_fallback_scan_at = 0.0
+        self._last_claude_fallback_scan_key = ""
+        self._claude_fallback_scan_interval_seconds = 10.0
         self._text_buffer = ""
         self._in_tool_use = False
         self._current_tool_input_parts = []
@@ -195,11 +203,76 @@ class ProgressTracker:
             self.is_active = True
 
         elif event_type == "system":
-            # System events (hooks, init, etc.) — track but don't count as messages
+            # System events (hooks, init, task notifications, etc.) — track but don't count as messages.
             self.event_format = self.event_format or "stream-json"
             subtype = event.get("subtype", "")
             if subtype == "init":
                 self.is_active = True
+                session_id = event.get("session_id")
+                if isinstance(session_id, str) and session_id.strip():
+                    self.claude_session_id = session_id.strip()
+                cwd = event.get("cwd")
+                if isinstance(cwd, str) and cwd.strip():
+                    self.claude_cwd = cwd.strip()
+            elif subtype == "task_started":
+                task_id = event.get("task_id")
+                if isinstance(task_id, str) and task_id.strip():
+                    self.claude_task_states[task_id.strip()] = {
+                        "status": "running",
+                        "summary": str(event.get("description") or "")[:120],
+                        "tool_use_id": str(event.get("tool_use_id") or ""),
+                        "task_type": str(event.get("task_type") or ""),
+                        "subagent_type": str(event.get("subagent_type") or ""),
+                    }
+                    self._update_claude_subagent_status_counts()
+            elif subtype in ("task_updated", "task_progress"):
+                task_id = event.get("task_id")
+                if isinstance(task_id, str) and task_id.strip():
+                    state = self.claude_task_states.setdefault(task_id.strip(), {})
+                    patch = event.get("patch") if isinstance(event.get("patch"), dict) else {}
+                    status = patch.get("status") or event.get("status")
+                    if status:
+                        state["status"] = str(status)
+                    summary = patch.get("summary") or patch.get("description") or event.get("summary") or event.get("description")
+                    if summary:
+                        state["summary"] = str(summary)[:120]
+                    else:
+                        state.setdefault("summary", "")
+                    tool_use_id = patch.get("tool_use_id") or event.get("tool_use_id")
+                    if tool_use_id:
+                        state["tool_use_id"] = str(tool_use_id)
+                    else:
+                        state.setdefault("tool_use_id", "")
+                    task_type = patch.get("task_type") or event.get("task_type")
+                    if task_type:
+                        state["task_type"] = str(task_type)
+                    else:
+                        state.setdefault("task_type", "")
+                    subagent_type = patch.get("subagent_type") or event.get("subagent_type")
+                    if subagent_type:
+                        state["subagent_type"] = str(subagent_type)
+                    else:
+                        state.setdefault("subagent_type", "")
+                    self._update_claude_subagent_status_counts()
+            elif subtype == "task_notification":
+                task_id = event.get("task_id")
+                if isinstance(task_id, str) and task_id.strip():
+                    state = self.claude_task_states.setdefault(task_id.strip(), {})
+                    status = event.get("status") or "completed"
+                    state["status"] = str(status)
+                    state["summary"] = str(event.get("summary") or state.get("summary") or "")[:120]
+                    state.setdefault("tool_use_id", str(event.get("tool_use_id") or ""))
+                    task_type = event.get("task_type")
+                    if task_type:
+                        state["task_type"] = str(task_type)
+                    else:
+                        state.setdefault("task_type", "")
+                    subagent_type = event.get("subagent_type")
+                    if subagent_type:
+                        state["subagent_type"] = str(subagent_type)
+                    else:
+                        state.setdefault("subagent_type", "")
+                    self._update_claude_subagent_status_counts()
 
         # ── Claude API raw stream format ────────────────────────────
         elif event_type == "message_start":
@@ -391,16 +464,135 @@ class ProgressTracker:
             pass
         return str(matches[0])
 
+    def _is_tracked_claude_subagent_state(self, state):
+        """Return true for Claude Code task events representing in-process agents."""
+        if not isinstance(state, dict):
+            return False
+        task_type = str(state.get("task_type") or "")
+        task_type_lower = task_type.lower()
+        subagent_type = str(state.get("subagent_type") or "")
+        if task_type_lower == "local_bash":
+            return False
+        tracked_types = {"in_process_teammate", "subagent", "agent", "teammate"}
+        if task_type_lower in tracked_types:
+            return True
+        if task_type_lower == "local_agent" and subagent_type:
+            return True
+        summary = str(state.get("summary") or "")
+        return bool(
+            not task_type
+            and summary.lower().startswith(("dev:", "critic:", "reviewer:", "agent:"))
+        )
+
+    def _has_tracked_claude_subagent_task(self):
+        """Return true once a Claude Code local-agent/subagent task has been observed."""
+        return any(
+            self._is_tracked_claude_subagent_state(state)
+            for state in self.claude_task_states.values()
+        )
+
+    def _update_claude_subagent_status_counts(self):
+        """Track Claude Code in-process teammate task state counts."""
+        counts = Counter()
+        active = 0
+        inactive_statuses = {
+            "completed",
+            "failed",
+            "cancelled",
+            "canceled",
+            "killed",
+            "stopped",
+            "success",
+            "error",
+        }
+        for state in self.claude_task_states.values():
+            if not self._is_tracked_claude_subagent_state(state):
+                continue
+            status = str(state.get("status") or "unknown")
+            counts[status] += 1
+            if status.lower() not in inactive_statuses:
+                active += 1
+            summary = state.get("summary") or state.get("subagent_type")
+            if summary:
+                self.last_text_snippet = str(summary).strip()[:120]
+                self._detect_phase(str(summary))
+        self.subagent_status_counts = counts
+        self.active_subagent_count = active
+
+    def _claude_projects_dir(self):
+        """Return the Claude Code projects directory for transcript lookup."""
+        projects_dir = os.environ.get("CLAUDE_PROJECTS_DIR")
+        if projects_dir:
+            return Path(projects_dir).expanduser()
+        claude_config_dir = os.environ.get("CLAUDE_CONFIG_DIR")
+        if claude_config_dir:
+            return Path(claude_config_dir).expanduser() / "projects"
+        claude_home = os.environ.get("CLAUDE_HOME")
+        if claude_home:
+            return Path(claude_home).expanduser() / "projects"
+        return Path.home() / ".claude" / "projects"
+
+    def _claude_project_key(self):
+        """Encode cwd the same way Claude Code stores project transcript dirs."""
+        cwd = self.claude_cwd
+        if not cwd:
+            return ""
+        return cwd.replace("\\", "-").replace("/", "-").replace(":", "")
+
+    def _find_claude_child_session_files(self):
+        """Find Claude Code subagent transcripts for this parent session."""
+        if not self.claude_session_id:
+            return []
+
+        projects_dir = self._claude_projects_dir()
+        if not projects_dir.exists():
+            return []
+
+        candidates = []
+        project_key = self._claude_project_key()
+        if project_key:
+            candidates.append(
+                projects_dir / project_key / self.claude_session_id / "subagents"
+            )
+
+        for candidate in candidates:
+            if candidate.exists():
+                try:
+                    return sorted(candidate.glob("*.jsonl"))
+                except OSError:
+                    return []
+
+        # Fallback for non-standard cwd encoding or custom Claude homes. Avoid
+        # repeatedly walking every stored transcript before any Agent task exists.
+        if not self._has_tracked_claude_subagent_task():
+            return []
+
+        fallback_scan_key = f"{projects_dir}:{self.claude_session_id}"
+        now = time.monotonic()
+        if (
+            self._last_claude_fallback_scan_key == fallback_scan_key
+            and now - self._last_claude_fallback_scan_at < self._claude_fallback_scan_interval_seconds
+        ):
+            return self._claude_child_session_files
+        self._last_claude_fallback_scan_key = fallback_scan_key
+        self._last_claude_fallback_scan_at = now
+        try:
+            matches = sorted(projects_dir.rglob(f"{self.claude_session_id}/subagents/*.jsonl"))
+        except OSError:
+            return []
+        return matches
+
     def refresh_child_session_activity(self, force=False):
-        """Refresh Codex child transcript file stats.
+        """Refresh child transcript file stats.
 
         The heartbeat monitor uses this activity signature to treat subagent
-        transcript growth as real progress while the parent Codex session is
-        blocked in `wait`.
+        transcript growth as real progress while the parent session is blocked
+        waiting for a child agent/tool result. Supports Codex child threads and
+        Claude Code in-process teammate transcripts.
         """
         previous_signature = self.child_activity_signature
 
-        if not self.codex_child_thread_ids:
+        if not self.codex_child_thread_ids and not self.claude_session_id:
             self.child_session_files = []
             self.child_total_bytes = 0
             self.child_activity_signature = ""
@@ -420,6 +612,7 @@ class ProgressTracker:
                     found = self._find_codex_child_session_file(thread_id)
                     if found:
                         self._codex_child_session_paths[thread_id] = found
+            self._claude_child_session_files = self._find_claude_child_session_files()
             self._last_child_scan_at = now
 
         files = []
@@ -427,24 +620,22 @@ class ProgressTracker:
         total_bytes = 0
         max_mtime = 0.0
 
-        for thread_id in sorted(self.codex_child_thread_ids):
-            path = self._codex_child_session_paths.get(thread_id)
-            if not path:
-                continue
+        def add_file(kind, identifier, path):
+            nonlocal total_bytes, max_mtime
             try:
                 stat = os.stat(path)
             except OSError:
-                continue
-
+                return
+            path_str = str(path)
             total_bytes += stat.st_size
             max_mtime = max(max_mtime, stat.st_mtime)
-            signature_parts.append(
-                f"{thread_id}:{stat.st_size}:{getattr(stat, 'st_mtime_ns', int(stat.st_mtime * 1_000_000_000))}"
-            )
+            mtime_ns = getattr(stat, "st_mtime_ns", int(stat.st_mtime * 1_000_000_000))
+            signature_parts.append(f"{kind}:{identifier}:{stat.st_size}:{mtime_ns}")
             files.append(
                 {
-                    "thread_id": thread_id,
-                    "path": path,
+                    "kind": kind,
+                    "thread_id": identifier,
+                    "path": path_str,
                     "size": stat.st_size,
                     "mtime": datetime.fromtimestamp(
                         stat.st_mtime, timezone.utc
@@ -452,6 +643,14 @@ class ProgressTracker:
                 }
             )
 
+        for thread_id in sorted(self.codex_child_thread_ids):
+            path = self._codex_child_session_paths.get(thread_id)
+            if path:
+                add_file("codex", thread_id, path)
+
+        for path in self._claude_child_session_files:
+            add_file("claude", path.stem, path)
+
         self.child_session_files = files
         self.child_total_bytes = total_bytes
         self.child_activity_signature = "|".join(signature_parts)
@@ -519,7 +718,7 @@ def atomic_write_json(data, filepath):
 
 def tail_and_parse(session_log, progress_file, poll_interval=0.5):
     """Tail session log and parse stream-json events."""
-    tracker = ProgressTracker()
+    tracker = ProgressTracker(session_log)
     last_write_state = None
 
     def state_key(state):

package/bundled/dev-pipeline-windows/templates/refactor-bootstrap-prompt.md

@@ -80,6 +80,12 @@ You are the **refactor session orchestrator**. Execute Refactor {{REFACTOR_ID}}:
 
 **YOU are the orchestrator. Execute each phase by spawning the appropriate team agent with run_in_background=false.**
 
+**Agent spawn failure policy (all Agent tool calls)**:
+- If spawning Dev or Reviewer fails with team/config/lock errors, retry at most once.
+- If the second attempt fails, do not keep spawning variants and do not enter artifact polling for Implementation Log, review-report, or refactor-report markers.
+- Use the documented inline/recovery fallback for that phase: complete remaining refactor work directly in the orchestrator when safe, write the required report yourself where possible, or write `failure-log.md` with the spawn error and last observable state before stopping for recovery.
+- Apply the same cap to any re-spawn for report repair or resume prompts; do not burn multiple minutes on identical team/config/lock failures.
+
 ## Workflow Checkpoint System
 
 A checkpoint file tracks your progress through this workflow:
@@ -164,6 +170,7 @@ Include browser verification approach in plan.md:
 **Goal**: Execute all tasks from plan.md while preserving existing behavior.
 
 - Spawn Dev agent (Agent tool, subagent_type="prizm-dev-team-dev", run_in_background=false)
+  Spawn failure cap: for team/config/lock errors, retry at most once for this Dev spawn. If the second attempt fails, do not poll for `## Implementation Log`; write `failure-log.md` and either complete remaining refactor work directly in the orchestrator or stop for recovery.
   Prompt: "Read {{DEV_SUBAGENT_PATH}}. For refactor {{REFACTOR_ID}} ('{{REFACTOR_TITLE}}'):
   1. Read `.prizmkit/refactor/{{REFACTOR_ID}}/spec.md` and `.prizmkit/refactor/{{REFACTOR_ID}}/plan.md`
   2. Read `.prizmkit/prizm-docs/` for affected modules (TRAPS, RULES, PATTERNS)
@@ -201,6 +208,7 @@ Include browser verification approach in plan.md:
 **Goal**: Verify refactoring quality and behavior preservation.
 
 - Spawn Reviewer agent (Agent tool, subagent_type="prizm-dev-team-reviewer", run_in_background=false)
+  Spawn failure cap: for team/config/lock errors, retry at most once for this Reviewer spawn. If the second attempt fails, do not poll for `review-report.md`; write `failure-log.md` with the spawn error and last observable state before stopping or performing an inline fallback.
   Prompt: "Read {{REVIEWER_SUBAGENT_PATH}}. For refactor {{REFACTOR_ID}}:
   1. Read `.prizmkit/refactor/{{REFACTOR_ID}}/spec.md` for goals and behavior preservation contracts
   2. Read `.prizmkit/refactor/{{REFACTOR_ID}}/plan.md` for architecture decisions and completed tasks
@@ -221,7 +229,20 @@ Include browser verification approach in plan.md:
   7. Report: verdict (PASS/NEEDS_FIXES), number of rounds, findings fixed/rejected
   "
 - **Wait for Reviewer to return**
-- Read `review-report.md` — if PASS proceed, if NEEDS_FIXES log remaining findings and proceed.
+- **Gate Check — Review Report**:
+  After Reviewer returns, verify the review report contains a verdict:
+  ```powershell
+  if (Select-String -Path .prizmkit/refactor/{{REFACTOR_ID}}/review-report.md -Pattern "## Verdict" -Quiet) { "GATE:PASS" } else { "GATE:MISSING" }
+  ```
+  If GATE:MISSING:
+  - Do not enter an unbounded report-repair loop and do not repeatedly re-spawn Reviewer.
+  - Perform one bounded status check; retry at most once: inspect the Reviewer output, `review-report.md` path, and any internal Reviewer/Dev spawn messages from `/prizmkit-code-review`.
+  - If the missing report is caused by team/config/lock errors from the Reviewer or internal Reviewer/Dev agent spawn, retry the Reviewer agent at most once only if it appears transient.
+  - If the report is still missing after that single check/retry, write `.prizmkit/refactor/{{REFACTOR_ID}}/failure-log.md` with the spawn/skill error and last observable state, then either perform a safe inline fallback review (spec/plan/diff/tests → write `review-report.md` with `## Verdict`) or stop with a clear recovery failure.
+
+Read `review-report.md` and check the Verdict:
+- `PASS` → proceed to next phase
+- `NEEDS_FIXES` → log remaining findings and proceed (do not retry externally)
 - **CP-RF-3**: Code review complete, tests pass, behavior preserved
 - **Checkpoint update**: set step `prizmkit-code-review` to `"completed"` in `{{CHECKPOINT_PATH}}`
 

package/bundled/dev-pipeline-windows/templates/sections/phase-critic-plan-full.md

@@ -8,6 +8,16 @@ If CRITIC:MISSING — skip this phase entirely and proceed. Log: "Critic agent n
 
 **Choose ONE path based on `{{CRITIC_COUNT}}`:**
 
+**Agent spawn failure policy**:
+- If spawning Critic fails with team/config/lock errors, retry at most once.
+- If the second attempt fails, do not keep spawning variants. Either create the required team once (when team tooling is available) or perform the plan challenge inline and write the required challenge report yourself.
+- Record the fallback in the report; do not burn multiple minutes on repeated identical spawn failures.
+
+**No silent report polling**:
+- Do NOT run a long no-output loop waiting for `challenge-report*.md`.
+- If you need to wait for a report file, use a short bounded check (≤120s) that prints elapsed time and reports present on every iteration.
+- If reports are still missing after the bounded check, request one status update; if still missing, perform the missing challenge lens inline and continue.
+
 **If {{CRITIC_COUNT}} = 1 → Single Critic** (skip to CP-2.5 after this):
 
 **Spawn Agent**:

package/bundled/dev-pipeline-windows/templates/sections/phase-critic-plan.md

@@ -16,6 +16,16 @@ If CRITIC:MISSING — skip this phase entirely and proceed. Log: "Critic agent n
 **Prompt**:
 > {{AGENT_PROMPT_CRITIC_PLAN_CHALLENGE}}
 
+**Agent spawn failure policy**:
+- If spawning Critic fails with team/config/lock errors, retry at most once.
+- If the second attempt fails, do not keep spawning variants. Either create the required team once (when team tooling is available) or perform the plan challenge inline and write `challenge-report.md` yourself.
+- Record the fallback in the report; do not burn multiple minutes on repeated identical spawn failures.
+
+**No silent report polling**:
+- Do NOT run a long no-output loop waiting for `challenge-report.md`.
+- If you need to wait for the report file, use a short bounded check (≤120s) that prints elapsed time and whether the report exists on every iteration.
+- If the report is still missing after the bounded check, request one status update; if still missing, perform the challenge inline and continue.
+
 Wait for Critic to return.
 - Read challenge-report.md. For items marked CRITICAL/HIGH: decide whether to adjust plan.md or document why the plan stands.
 - Max 1 plan revision round.

package/bundled/dev-pipeline-windows/templates/sections/phase-implement-agent.md

@@ -15,11 +15,23 @@
 | subagent_type | prizm-dev-team-dev |
 | run_in_background | false |
 
+**Agent spawn failure policy**:
+- If spawning Dev fails with team/config/lock errors, retry at most once.
+- If the second attempt fails, do not enter Implementation Log polling or repeated recovery spawn loops.
+- Use the documented inline/recovery fallback: write `failure-log.md` with the spawn error and last observable state, then either complete remaining tasks directly in the orchestrator or stop with a clear failure for recovery.
+- Apply the same cap to Dev re-spawns for Implementation Log repair or resume prompts; do not burn multiple minutes on identical team/config/lock failures.
+
 **Prompt**:
 > {{AGENT_PROMPT_DEV_IMPLEMENT}}
 
 Wait for Dev to return. All tasks must be `[x]`, tests pass.
 
+**No silent artifact polling**:
+- Do NOT run a long no-output loop that only waits for `## Implementation Log` or any other file marker.
+- If you must wait for Dev after spawning or sending a status request, use short bounded checks (≤120s) that print a heartbeat line each iteration with: elapsed time, remaining unchecked task count, whether `## Implementation Log` exists, and whether `git diff --stat` changed.
+- If Dev has no transcript/file/diff progress for one bounded check, send one status request. If there is still no progress on the next bounded check, stop waiting, write `failure-log.md` with the last observable state, and follow Subagent Timeout Recovery.
+- Prefer the Agent tool's completion notification or Dev's `COMPLETION_SIGNAL`; file presence alone is not a liveness signal.
+
 **Gate Check — Implementation Log**:
 After Dev agent returns, verify the Implementation Log was written:
 ```powershell

package/bundled/dev-pipeline-windows/templates/sections/phase-implement-full.md

@@ -22,9 +22,21 @@ Select-String -Pattern '^\- \[ \]' .prizmkit/specs/{{FEATURE_SLUG}}/plan.md 2>$n
 | subagent_type | prizm-dev-team-dev |
 | run_in_background | false |
 
+**Agent spawn failure policy**:
+- If spawning Dev fails with team/config/lock errors, retry at most once.
+- If the second attempt fails, do not enter Implementation Log polling or repeated recovery spawn loops.
+- Use the documented inline/recovery fallback: write `failure-log.md` with the spawn error and last observable state, then either complete remaining tasks directly in the orchestrator or stop with a clear failure for recovery.
+- Apply the same cap to Dev re-spawns for Implementation Log repair or resume prompts; do not burn multiple minutes on identical team/config/lock failures.
+
 **Prompt**:
 > {{AGENT_PROMPT_DEV_IMPLEMENT}}
 
+**No silent artifact polling**:
+- Do NOT run a long no-output loop that only waits for `## Implementation Log` or any other file marker.
+- If you must wait for Dev after spawning or sending a status request, use short bounded checks (≤120s) that print a heartbeat line each iteration with: elapsed time, remaining unchecked task count, whether `## Implementation Log` exists, and whether `git diff --stat` changed.
+- If Dev has no transcript/file/diff progress for one bounded check, send one status request. If there is still no progress on the next bounded check, stop waiting, write `failure-log.md` with the last observable state, and follow Subagent Timeout Recovery.
+- Prefer the Agent tool's completion notification or Dev's `COMPLETION_SIGNAL`; file presence alone is not a liveness signal.
+
 **Gate Check — Implementation Log**:
 After Dev agent returns, verify the Implementation Log was written:
 ```powershell

package/bundled/dev-pipeline-windows/templates/sections/phase-review-agent.md

@@ -9,7 +9,11 @@ After `/prizmkit-code-review` returns, verify the review report:
 ```powershell
 if (Select-String -Path .prizmkit/specs/{{FEATURE_SLUG}}/review-report.md -Pattern "## Verdict" -Quiet) { "GATE:PASS" } else { "GATE:MISSING" }
 ```
-If GATE:MISSING — re-run `/prizmkit-code-review`.
+If GATE:MISSING:
+- Do not re-run `/prizmkit-code-review` in an unbounded report-repair loop.
+- Perform one bounded status check; retry at most once: inspect the skill output, `review-report.md` path, and any Reviewer/Dev spawn messages.
+- If the missing report is caused by team/config/lock errors from the internal Reviewer/Dev agent spawn, retry `/prizmkit-code-review` at most once only if it appears transient.
+- If the report is still missing after that single check/retry, write `failure-log.md` with the spawn/skill error and last observable state, then either perform a safe inline fallback review (spec/plan/diff/tests → write `review-report.md` with `## Verdict`) or stop with a clear recovery failure.
 
 Read `review-report.md` and check the Verdict:
 - `PASS` → proceed to next phase

package/bundled/dev-pipeline-windows/templates/sections/phase-review-full.md

@@ -9,7 +9,11 @@ After `/prizmkit-code-review` returns, verify the review report:
 ```powershell
 if (Select-String -Path .prizmkit/specs/{{FEATURE_SLUG}}/review-report.md -Pattern "## Verdict" -Quiet) { "GATE:PASS" } else { "GATE:MISSING" }
 ```
-If GATE:MISSING — re-run `/prizmkit-code-review`.
+If GATE:MISSING:
+- Do not re-run `/prizmkit-code-review` in an unbounded report-repair loop.
+- Perform one bounded status check; retry at most once: inspect the skill output, `review-report.md` path, and any Reviewer/Dev spawn messages.
+- If the missing report is caused by team/config/lock errors from the internal Reviewer/Dev agent spawn, retry `/prizmkit-code-review` at most once only if it appears transient.
+- If the report is still missing after that single check/retry, write `failure-log.md` with the spawn/skill error and last observable state, then either perform a safe inline fallback review (spec/plan/diff/tests → write `review-report.md` with `## Verdict`) or stop with a clear recovery failure.
 
 Read `review-report.md` and check the Verdict:
 - `PASS` → proceed to next phase

package/bundled/skills/_metadata.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.1.68",
+  "version": "1.1.69",
   "skills": {
     "prizm-kit": {
       "description": "Full-lifecycle dev toolkit. Covers spec-driven development, Prizm context docs, code quality, debugging, deployment, and knowledge management.",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "prizmkit",
-  "version": "1.1.68",
+  "version": "1.1.69",
   "description": "Create a new PrizmKit-powered project with clean initialization — no framework dev files, just what you need.",
   "type": "module",
   "bin": {