prizmkit 1.1.114 → 1.1.116

package/bundled/dev-pipeline/scripts/update-checkpoint.py

@@ -12,7 +12,7 @@ Usage:
 
 Exit codes:
   0 = success
-  1 = validation error (step not found, invalid status, etc.)
+  1 = validation error (step not found, invalid status, ambiguous skill, etc.)
   2 = file error (not found, corrupted JSON)
 
 Output (stdout): JSON with {ok: true, step_id, skill, old_status, new_status} or {ok: false, error}
@@ -24,13 +24,27 @@ import os
 import sys
 import tempfile
 
-VALID_STATUSES = {"pending", "in_progress", "completed", "skipped", "failed"}
+_PIPELINE_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
+if _PIPELINE_ROOT not in sys.path:
+    sys.path.insert(0, _PIPELINE_ROOT)
+
+from prizmkit_runtime.checkpoint_state import (  # noqa: E402
+    STEP_ID_PATTERN,
+    VALID_CHECKPOINT_STATUSES,
+    load_checkpoint_state,
+)
+
+VALID_STATUSES = VALID_CHECKPOINT_STATUSES
 
 
 def _load_checkpoint(path):
-    """Load checkpoint JSON. Returns (data, error_string)."""
-    if not os.path.isfile(path):
-        return None, "File not found: {}".format(path)
+    """Load checkpoint JSON after shared structural validation."""
+    state = load_checkpoint_state(path)
+    if not state.valid:
+        return None, "Invalid checkpoint ({}): {}".format(
+            state.error_code,
+            state.error_message,
+        )
     try:
         with open(path, "r", encoding="utf-8") as f:
             data = json.load(f)
@@ -38,9 +52,6 @@ def _load_checkpoint(path):
         return None, "Corrupted JSON: {}".format(e)
     except IOError as e:
         return None, "Cannot read file: {}".format(e)
-
-    if "steps" not in data or not isinstance(data["steps"], list):
-        return None, "Invalid checkpoint: missing 'steps' array"
     return data, None
 
 
@@ -60,7 +71,6 @@ def _write_checkpoint(path, data):
             f.write("\n")
         os.replace(tmp_path, os.path.abspath(path))
     except (IOError, OSError) as e:
-        # Clean up temp file on error
         if tmp_path is not None and os.path.exists(tmp_path):
             os.unlink(tmp_path)
         return "Cannot write file: {}".format(e)
@@ -68,14 +78,29 @@ def _write_checkpoint(path, data):
 
 
 def _find_step(steps, identifier):
-    """Find a step by skill name or step ID.
-
-    Returns (index, step_dict) or (None, None).
-    """
-    for i, step in enumerate(steps):
-        if step.get("skill") == identifier or step.get("id") == identifier:
-            return i, step
-    return None, None
+    """Find a step by exact ID or unambiguous skill name."""
+    if STEP_ID_PATTERN.match(identifier):
+        for i, step in enumerate(steps):
+            if step.get("id") == identifier:
+                return i, step, None
+        return None, None, "Step '{}' not found.".format(identifier)
+
+    matches = [
+        (i, step)
+        for i, step in enumerate(steps)
+        if step.get("skill") == identifier
+    ]
+    if len(matches) == 1:
+        index, step = matches[0]
+        return index, step, None
+    if len(matches) > 1:
+        ids = [str(step.get("id")) for _index, step in matches]
+        example = ids[0] if ids else "SNN"
+        return None, None, (
+            "Step '{}' matches multiple checkpoint steps ({}). "
+            "Use an explicit step ID such as {}."
+        ).format(identifier, ", ".join(ids), example)
+    return None, None, "Step '{}' not found.".format(identifier)
 
 
 def update_checkpoint(checkpoint_path, step_identifier, new_status, note=None):
@@ -95,17 +120,16 @@ def update_checkpoint(checkpoint_path, step_identifier, new_status, note=None):
     if err:
         return {"ok": False, "error": err}
 
-    idx, step = _find_step(data["steps"], step_identifier)
+    idx, step, find_error = _find_step(data["steps"], step_identifier)
     if step is None:
         available = [
             "{} ({})".format(s.get("id", "?"), s.get("skill", "?"))
             for s in data["steps"]
         ]
+        suffix = " Available: {}".format(", ".join(available)) if available else ""
         return {
             "ok": False,
-            "error": "Step '{}' not found. Available: {}".format(
-                step_identifier, ", ".join(available)
-            ),
+            "error": "{}{}".format(find_error or "Step not found.", suffix),
         }
 
     old_status = step.get("status", "unknown")
@@ -166,7 +190,15 @@ def main():
         args.checkpoint_path, args.step, args.status, args.note
     )
     print(json.dumps(result, indent=2, ensure_ascii=False))
-    return 0 if result.get("ok") else (2 if "File not found" in result.get("error", "") or "Corrupted" in result.get("error", "") else 1)
+    error = result.get("error", "")
+    file_error = (
+        error.startswith("Invalid checkpoint (missing)")
+        or error.startswith("Invalid checkpoint (malformed_json)")
+        or error.startswith("Invalid checkpoint (read_error)")
+        or error.startswith("Corrupted JSON")
+        or error.startswith("Cannot read file")
+    )
+    return 0 if result.get("ok") else (2 if file_error else 1)
 
 
 if __name__ == "__main__":

package/bundled/dev-pipeline/scripts/update-feature-status.py

@@ -337,11 +337,8 @@ def _read_feature_checkpoint_phase(project_root, feature_slug):
 
 
 def _checkpoint_phase_or_cached(project_root, feature_slug, status_data):
-    """Return live checkpoint phase, falling back to cached status data."""
-    checkpoint_phase = _read_feature_checkpoint_phase(project_root, feature_slug)
-    if checkpoint_phase is not None:
-        return checkpoint_phase
-    return status_data.get("resume_from_phase")
+    """Return live checkpoint phase from the authoritative checkpoint only."""
+    return _read_feature_checkpoint_phase(project_root, feature_slug)
 
 
 def _sync_checkpoint_phase(project_root, feature_slug, status_data):
@@ -1263,8 +1260,7 @@ def action_status(feature_list_data, state_dir, feature_filter=None, project_roo
         fstatus = feature.get("status", "pending")
         fs = load_feature_status(state_dir, fid)
         feature_slug = _build_feature_slug(fid, title)
-        # Read phase cursor from checkpoint (single source of truth). The
-        # status.json field is only a cache/fallback for missing checkpoints.
+        # Read phase cursor from checkpoint (authoritative when valid).
         resume_phase = _checkpoint_phase_or_cached(project_root, feature_slug, fs)
         if resume_phase != fs.get("resume_from_phase"):
             fs["resume_from_phase"] = resume_phase

package/bundled/dev-pipeline/scripts/update-refactor-status.py

@@ -231,11 +231,8 @@ def _read_refactor_checkpoint_phase(project_root, refactor_id):
 
 
 def _checkpoint_phase_or_cached(project_root, refactor_id, status_data):
-    """Return live checkpoint phase, falling back to cached status data."""
-    checkpoint_phase = _read_refactor_checkpoint_phase(project_root, refactor_id)
-    if checkpoint_phase is not None:
-        return checkpoint_phase
-    return status_data.get("resume_from_phase")
+    """Return live checkpoint phase from the authoritative checkpoint only."""
+    return _read_refactor_checkpoint_phase(project_root, refactor_id)
 
 
 def _sync_checkpoint_phase(project_root, refactor_id, status_data):
@@ -885,8 +882,7 @@ def action_status(refactor_list_data, state_dir, project_root=None):
         rs = load_refactor_status(state_dir, rid)
         retry_count = rs.get("retry_count", 0)
         max_retries_val = rs.get("max_retries", 3)
-        # Read phase cursor from checkpoint (single source of truth). The
-        # status.json field is only a cache/fallback for missing checkpoints.
+        # Read phase cursor from checkpoint (authoritative when valid).
         resume_phase = _checkpoint_phase_or_cached(project_root, rid, rs)
         if resume_phase != rs.get("resume_from_phase"):
             rs["resume_from_phase"] = resume_phase

package/bundled/dev-pipeline/scripts/utils.py

@@ -16,6 +16,10 @@ _PIPELINE_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
 if _PIPELINE_ROOT not in sys.path:
     sys.path.insert(0, _PIPELINE_ROOT)
 
+from prizmkit_runtime.checkpoint_state import (  # noqa: E402
+    read_checkpoint_cursor as shared_read_checkpoint_cursor,
+)
+
 
 def shell_quote(value):
     """Return a shell-safe token for prompt command examples."""
@@ -773,40 +777,5 @@ def read_platform_conventions(project_root):
 
 
 def read_checkpoint_cursor(checkpoint_path):
-    """Read the phase cursor from a workflow-checkpoint.json file.
-
-    Returns the first non-completed/skipped step's step index (e.g., 3 for S03).
-    If every step is completed or skipped, returns the last completed/skipped
-    step index. Returns None if the file does not exist or is unreadable.
-
-    The cursor is what gets displayed as "CP-BF-<n>" in the terminal status.
-    """
-    if not os.path.isfile(checkpoint_path):
-        return None
-    try:
-        with open(checkpoint_path, "r", encoding="utf-8") as f:
-            data = json.load(f)
-    except (json.JSONDecodeError, IOError):
-        return None
-    if not isinstance(data, dict):
-        return None
-    steps = data.get("steps")
-    if not isinstance(steps, list):
-        return None
-    last_completed = 0
-    for step in steps:
-        if not isinstance(step, dict):
-            continue
-        status = step.get("status", "pending")
-        sid = step.get("id", "")
-        try:
-            step_num = int(sid.lstrip("S"))
-        except (ValueError, AttributeError):
-            continue
-        if status in ("completed", "skipped"):
-            last_completed = max(last_completed, step_num)
-        else:
-            # Return the first non-completed step's number
-            return step_num
-    # All steps are completed — return the last step number
-    return last_completed if last_completed > 0 else None
+    """Read the phase cursor from a valid workflow-checkpoint.json file."""
+    return shared_read_checkpoint_cursor(checkpoint_path)

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

@@ -44,7 +44,7 @@ Infer what needs to be done from the feature context above and follow the standa
 - Do NOT push to remote — the user will push manually.
 - Write all artifacts to `.prizmkit/specs/{{FEATURE_SLUG}}/`.
 - If a step fails after 3 attempts, write a status report and stop.
-- **Never re-read unmodified files**: once you read a file into context, do NOT read it again unless it was modified by an Edit/Write after your last read — use `grep -n`/`sed -n` for specific lines. Before issuing a Read, ask: "Have I read this file before, and has it changed since?" If no — do NOT read it. Subagents (Critic, Reviewer) must rely on context-snapshot.md rather than re-reading files the orchestrator already read.
+- **Never re-read unmodified files**: once you read a file into context, do NOT read it again unless it was modified by an Edit/Write after your last read — use `grep -n`/`sed -n` for specific lines. Before issuing a Read, ask: "Have I read this file before, and has it changed since?" If no — do NOT read it. Reviewer subagents must rely on context-snapshot.md rather than re-reading files the orchestrator already read.
 - **Read offset safety**: if Read returns "shorter than offset"/"empty" — run `wc -l` then `sed -n`, do NOT retry same offset.
 - **Hard Round Cap**: after 6 total test-fix rounds, STOP trial-and-error. Switch to read-once-then-rewrite. Do NOT exceed 7 rounds.
 - **Layered test**: debug with single-file tests, only run full suite as gate when single-file is green.

package/bundled/dev-pipeline/templates/bootstrap-tier1.md

@@ -46,7 +46,7 @@ You are running in **headless non-interactive mode** with a FINITE context windo
 
 1. **context-snapshot.md is your single source of truth** — After Phase 1 builds it, ALWAYS read context-snapshot.md instead of re-reading individual source files
 2. **Never re-read your own writes** — After you create/modify a file, do NOT read it back to verify. Trust your write was correct.
-3. **Never re-read unmodified files** — Once you have read a file into context, do NOT read it again unless it was modified by an Edit/Write operation after your last read. Use platform file/search tools for targeted lookup; when shell-free helper lookup is needed, run `{{RUNTIME_HELPER_CMD}} text search <file> --pattern "<pattern>" --json`, then read only the smallest bounded range with the platform file-reading tool instead of full-file Read. Before issuing a Read, ask yourself: "Have I read this file before, and has it changed since?" If the answer is "no, it hasn't changed" — do NOT read it. This applies to all files including those summarized in context-snapshot.md Section 4. Subagents (Critic, Reviewer) must receive context-snapshot.md and rely on it rather than independently re-reading the same files the orchestrator already read.
+3. **Never re-read unmodified files** — Once you have read a file into context, do NOT read it again unless it was modified by an Edit/Write operation after your last read. Use platform file/search tools for targeted lookup; when shell-free helper lookup is needed, run `{{RUNTIME_HELPER_CMD}} text search <file> --pattern "<pattern>" --json`, then read only the smallest bounded range with the platform file-reading tool instead of full-file Read. Before issuing a Read, ask yourself: "Have I read this file before, and has it changed since?" If the answer is "no, it hasn't changed" — do NOT read it. This applies to all files including those summarized in context-snapshot.md Section 4. Reviewer subagents must receive context-snapshot.md and rely on it rather than independently re-reading the same files the orchestrator already read.
 4. **Stay focused** — Do NOT explore code unrelated to this feature. No curiosity-driven reads.
 4. **One task at a time** — In Phase 3 (implement), complete and test one task before starting the next.
 5. **Minimize tool output** — Never load full command output into context. First capture command output to a temp file using the command/tool output option or the host-appropriate redirection, then inspect only the final relevant lines and use targeted search helpers to extract the information needed for the current task. Only read the filtered result — never the raw full output.

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

@@ -1,4 +1,4 @@
-# Dev-Pipeline Session Bootstrap — Tier 2 (Orchestrator + Critic/Reviewer)
+# Dev-Pipeline Session Bootstrap — Tier 2 (Orchestrator + Reviewer)
 
 ## Session Context
 
@@ -10,12 +10,12 @@
 
 You are the **session orchestrator**. Implement Feature {{FEATURE_ID}}: "{{FEATURE_TITLE}}".
 
-**CRITICAL**: You MUST NOT exit until ALL work is complete and committed. When you spawn Critic or Reviewer agents, wait for each to finish (run_in_background=false).
+**CRITICAL**: You MUST NOT exit until ALL work is complete and committed. When you spawn Reviewer agents, wait for each to finish (run_in_background=false).
 
-**Tier 2 — Orchestrator + Critic**: You handle context, planning, and implementation directly. Critic challenges the plan when enabled. Do not spawn top-level Dev or Reviewer subagents; code review runs later through `/prizmkit-code-review`.
+**Tier 2 — Orchestrator + Reviewer**: You handle context, planning, and implementation directly. Do not spawn top-level Dev or Reviewer subagents; code review runs later through `/prizmkit-code-review`.
 
 **Agent spawn failure policy (all Agent tool calls)**:
-- If spawning Reviewer or Critic fails with team/config/lock errors, retry at most once.
+- If spawning 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, challenge report, or review report markers.
 - Use the documented inline/recovery fallback for that phase: write the required report yourself where possible, complete remaining 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.
@@ -52,7 +52,7 @@ You are running in **headless non-interactive mode** with a FINITE context windo
 
 1. **context-snapshot.md is your single source of truth** — After Phase 1 builds it, ALWAYS read context-snapshot.md instead of re-reading individual source files
 2. **Never re-read your own writes** — After you create/modify a file, do NOT read it back to verify. Trust your write was correct.
-3. **Never re-read unmodified files** — Once you have read a file into context, do NOT read it again unless it was modified by an Edit/Write operation after your last read. Use platform file/search tools for targeted lookup; when shell-free helper lookup is needed, run `{{RUNTIME_HELPER_CMD}} text search <file> --pattern "<pattern>" --json`, then read only the smallest bounded range with the platform file-reading tool instead of full-file Read. Before issuing a Read, ask yourself: "Have I read this file before, and has it changed since?" If the answer is "no, it hasn't changed" — do NOT read it. This applies to all files including those summarized in context-snapshot.md Section 4. Subagents (Critic, Reviewer) must receive context-snapshot.md and rely on it rather than independently re-reading the same files the orchestrator already read.
+3. **Never re-read unmodified files** — Once you have read a file into context, do NOT read it again unless it was modified by an Edit/Write operation after your last read. Use platform file/search tools for targeted lookup; when shell-free helper lookup is needed, run `{{RUNTIME_HELPER_CMD}} text search <file> --pattern "<pattern>" --json`, then read only the smallest bounded range with the platform file-reading tool instead of full-file Read. Before issuing a Read, ask yourself: "Have I read this file before, and has it changed since?" If the answer is "no, it hasn't changed" — do NOT read it. This applies to all files including those summarized in context-snapshot.md Section 4. Reviewer subagents must receive context-snapshot.md and rely on it rather than independently re-reading the same files the orchestrator already read.
 4. **Stay focused** — Do NOT explore code unrelated to this feature. No curiosity-driven reads.
 4. **One task at a time** — In Phase 4 (implement), complete and test one task before starting the next.
 5. **Minimize tool output** — Never load full command output into context. First capture command output to a temp file using the command/tool output option or the host-appropriate redirection, then inspect only the final relevant lines and use targeted search helpers to extract the information needed for the current task. Only read the filtered result — never the raw full output.
@@ -171,85 +171,6 @@ Do not spawn a top-level Reviewer subagent for planning analysis. Perform a boun
 
 **CP-2**: Plan self-check complete; no CRITICAL plan issues remain.
 
-{{IF_CRITIC_ENABLED}}
-### Phase 3.5: Plan Challenge — Critic Agent(s)
-
-**Guard**: Verify critic agent file exists before spawning:
-```bash
-{{RUNTIME_HELPER_CMD}} artifact exists {{CRITIC_SUBAGENT_PATH}} --exists-marker CRITIC:READY --missing-marker CRITIC:MISSING
-```
-If CRITIC:MISSING — skip Phase 3.5 entirely and proceed to Phase 4. Log: "Critic agent not installed — skipping Plan Challenge."
-
-**Choose ONE path based on `{{CRITIC_COUNT}}`:**
-
-**If {{CRITIC_COUNT}} = 1 → Single Critic** (skip to CP-2.5 after this):
-
-Spawn Critic agent (Agent tool, subagent_type="prizm-dev-team-critic", mode="plan", run_in_background=false, isolation=default/no worktree). Do not request worktree isolation; this prevents AI tool-created `.claude/worktrees/...` subagent worktrees. PrizmKit pipeline-managed linked git worktrees under `.prizmkit/state/worktrees/...` are separate and controlled by `USE_WORKTREE`.
-
-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**
-> 1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST — Section 3 has project context, Section 4 has file manifest.
-> 2. Use context-snapshot.md as the shared source of truth. Do not create or enter AI tool-created `.claude/worktrees/...` subagent worktrees; use default/no worktree isolation and do not request worktree isolation.
-> 3. PrizmKit pipeline-managed linked git worktrees under `.prizmkit/state/worktrees/...` are a separate runner feature controlled by `USE_WORKTREE`; do not confuse them with AI tool-created `.claude/worktrees/...`.
-> 4. Read additional `.prizmkit/prizm-docs/` or source excerpts only when needed to verify a specific challenge.
-> 5. Challenge plan.md against the project's existing architecture, patterns, and style.
-> Write `.prizmkit/specs/{{FEATURE_SLUG}}/challenge-report.md` with findings (or 'No significant challenges')."
-
-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.
-
-**If {{CRITIC_COUNT}} = 3 → Multi-Critic Voting** (skip Single Critic above):
-
-**IMPORTANT**: Spawn all 3 Critics in PARALLEL (issue all 3 Agent tool calls in the SAME message turn). Do NOT wait for one before spawning the next.
-
-Spawn Critic-A, Critic-B, Critic-C simultaneously (each with mode="plan", run_in_background=false, isolation=default/no worktree). Do not request worktree isolation; this prevents AI tool-created `.claude/worktrees/...` subagent worktrees. PrizmKit pipeline-managed linked git worktrees under `.prizmkit/state/worktrees/...` are separate and controlled by `USE_WORKTREE`:
-
-Critic-A prompt:
-> "Read {{CRITIC_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
-> **MODE: Plan Challenge — Lens: Architecture & Scalability**
-> Focus on: architectural pattern fit, scalability implications, over-engineering risks, component boundary design.
-> 1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST — Section 3 has TRAPS/RULES, Section 4 has file manifest.
-> 2. Use context-snapshot.md as the shared source of truth. Do not create or enter AI tool-created `.claude/worktrees/...` subagent worktrees; use default/no worktree isolation and do not request worktree isolation.
-> 3. PrizmKit pipeline-managed linked git worktrees under `.prizmkit/state/worktrees/...` are a separate runner feature controlled by `USE_WORKTREE`; do not confuse them with AI tool-created `.claude/worktrees/...`.
-> 4. Read additional `.prizmkit/prizm-docs/` or source excerpts only when needed to verify a specific challenge.
-> 4. Challenge plan.md through your architecture lens.
-> Write `.prizmkit/specs/{{FEATURE_SLUG}}/challenge-report-A.md`."
-
-Critic-B prompt:
-> "Read {{CRITIC_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
-> **MODE: Plan Challenge — Lens: Data Model & Edge Cases**
-> Focus on: data model design fit, entity relationships, edge cases in business logic, missing boundary conditions.
-> 1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST — Section 3 has TRAPS/RULES, Section 4 has file manifest.
-> 2. Use context-snapshot.md as the shared source of truth. Do not create or enter AI tool-created `.claude/worktrees/...` subagent worktrees; use default/no worktree isolation and do not request worktree isolation.
-> 3. PrizmKit pipeline-managed linked git worktrees under `.prizmkit/state/worktrees/...` are a separate runner feature controlled by `USE_WORKTREE`; do not confuse them with AI tool-created `.claude/worktrees/...`.
-> 4. Read additional `.prizmkit/prizm-docs/` or source excerpts only when needed to verify a specific challenge.
-> 4. Challenge plan.md through your data/edge-case lens.
-> Write `.prizmkit/specs/{{FEATURE_SLUG}}/challenge-report-B.md`."
-
-Critic-C prompt:
-> "Read {{CRITIC_SUBAGENT_PATH}}. For feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}):
-> **MODE: Plan Challenge — Lens: Security & Performance**
-> Focus on: security attack surface, authentication/authorization gaps, performance bottlenecks, resource leaks.
-> 1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST — Section 3 has TRAPS/RULES, Section 4 has file manifest.
-> 2. Use context-snapshot.md as the shared source of truth. Do not create or enter AI tool-created `.claude/worktrees/...` subagent worktrees; use default/no worktree isolation and do not request worktree isolation.
-> 3. PrizmKit pipeline-managed linked git worktrees under `.prizmkit/state/worktrees/...` are a separate runner feature controlled by `USE_WORKTREE`; do not confuse them with AI tool-created `.claude/worktrees/...`.
-> 4. Read additional `.prizmkit/prizm-docs/` or source excerpts only when needed to verify a specific challenge.
-> 4. Challenge plan.md through your security/performance lens.
-> Write `.prizmkit/specs/{{FEATURE_SLUG}}/challenge-report-C.md`."
-
-Spawn failure cap: for team/config/lock errors, each Critic retries at most once. If 2 or more Critics fail to spawn after retry, perform the plan challenge inline and record the fallback.
-
-After all critics return, read all 3 reports:
-- Challenge raised by **2/3 or more** critics → **must respond** (adjust plan or justify why not)
-- Challenge raised by **1/3 only** → logged in context-snapshot but not blocking
-- Max 1 plan revision round.
-
-**CP-2.5**: Plan challenges reviewed and resolved.
-{{END_IF_CRITIC_ENABLED}}
 
 ### Implement — Orchestrator Direct (no Dev subagent)
 
@@ -270,7 +191,7 @@ Before starting, check plan.md Tasks:
 - Implements task-by-task, marking each `[x]` immediately
 - Creates/updates L2 `.prizm` docs when creating new modules
 - Defers scoped/full test execution until after the code-review loop completes
-- Preserves Reviewer/Critic behavior; only the top-level implementation Dev handoff is removed
+- Preserves Reviewer behavior; only the top-level implementation Dev handoff is removed
 - If plan.md has >5 tasks: update checkpoints after every 3 tasks
 
 **3b. Focused checks only (no test gate here)**:
@@ -300,7 +221,7 @@ For each Verification Gate from the Task Contract, write one evidence line to Im
 
 Review the completed implementation before the scoped feature test gate runs. Use `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/` so the code-review skill can read spec, plan, context snapshot, implementation log, and current diff artifacts. Do not require or read a prior `/prizmkit-test` report here; test generation and test-fix looping happen in the next phase.
 
-Run `/prizmkit-code-review` with `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/`.
+Run `/prizmkit-code-review` with `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/`. The code-review skill must launch Reviewer in `current-workspace / active-checkout / no-worktree` mode so it reviews the active checkout rather than an isolated copy; do not request worktree isolation or use `.claude/worktrees/...` / `.prizmkit/state/worktrees/...`. Do not set `USE_WORKTREE` for reviewer launches.
 
 The skill runs an internal review-fix loop (Reviewer Agent → filter → orchestrator fix, max 3 rounds) and writes `review-report.md` to the artifact directory.
 
@@ -554,9 +475,6 @@ Rules for writing completion notes:
 |----------|------|
 | Feature Artifacts Dir | `.prizmkit/specs/{{FEATURE_SLUG}}/` |
 | Context Snapshot | `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` |
-{{IF_CRITIC_ENABLED}}
-| Critic Agent Def | {{CRITIC_SUBAGENT_PATH}} |
-{{END_IF_CRITIC_ENABLED}}
 | Project Root | {{PROJECT_ROOT}} |
 
 ## Failure Capture Protocol
@@ -578,11 +496,11 @@ If you encounter an unrecoverable error, context overflow, or are about to exit
 
 ## Reminders
 
-- Tier 2: orchestrator builds context+plan and implements directly; Critic challenges plan when enabled; `/prizmkit-code-review` handles review later
+- Tier 2: orchestrator builds context+plan and implements directly; `/prizmkit-code-review` handles review later
 - Build context-snapshot.md FIRST; use it throughout instead of re-reading source files
 - context-snapshot.md is append-only: orchestrator writes Sections 1-4 + Implementation Log, Reviewer appends Review Notes
 - Gate checks enforce Implementation Log and Review Notes are written before proceeding
-- Do NOT use `run_in_background=true` when spawning Critic agents
+- Do NOT use `run_in_background=true` when spawning Reviewer agents
 - **NEVER delete, modify, or touch any file under `.prizmkit/state/`** — those are pipeline runtime files managed by the runner
 - NEVER run `rm -rf`, `git clean`, or any destructive filesystem operations
 - `/prizmkit-committer` is mandatory, and must not be replaced with manual git commit commands

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

@@ -1,4 +1,4 @@
-# Dev-Pipeline Session Bootstrap — Tier 3 (Orchestrator + Critic/Reviewer)
+# Dev-Pipeline Session Bootstrap — Tier 3 (Orchestrator + Reviewer)
 
 ## Session Context
 
@@ -10,12 +10,12 @@
 
 You are the **session orchestrator**. Implement Feature {{FEATURE_ID}}: "{{FEATURE_TITLE}}".
 
-**CRITICAL**: You MUST NOT exit until ALL work is complete and committed. When you spawn Critic or Reviewer agents, wait for each to finish (run_in_background=false). Do NOT spawn agents in background and exit — that kills the session.
+**CRITICAL**: You MUST NOT exit until ALL work is complete and committed. When you spawn Reviewer agents, wait for each to finish (run_in_background=false). Do NOT spawn agents in background and exit — that kills the session.
 
-**Tier 3 — Orchestrator + Critic**: For complex features, the main orchestrator handles context, planning, and implementation directly. Critic challenges the plan. Do not spawn top-level Dev or Reviewer subagents; code review runs later through `/prizmkit-code-review`.
+**Tier 3 — Orchestrator + Reviewer**: For complex features, the main orchestrator handles context, planning, and implementation directly. Do not spawn top-level Dev or Reviewer subagents; code review runs later through `/prizmkit-code-review`.
 
 **Agent spawn failure policy (all Agent tool calls)**:
-- If spawning Reviewer or Critic fails with team/config/lock errors, retry at most once.
+- If spawning 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, challenge report, or review report markers.
 - Use the documented inline/recovery fallback for that phase: write the required report yourself where possible, complete remaining 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.
@@ -52,7 +52,7 @@ You are running in **headless non-interactive mode** with a FINITE context windo
 
 1. **context-snapshot.md is your single source of truth** — After Phase 1-2 builds it, ALWAYS read context-snapshot.md instead of re-reading individual source files
 2. **Never re-read your own writes** — After you create/modify a file, do NOT read it back to verify. Trust your write was correct.
-3. **Never re-read unmodified files** — Once you have read a file into context, do NOT read it again unless it was modified by an Edit/Write operation after your last read. Use platform file/search tools for targeted lookup; when shell-free helper lookup is needed, run `{{RUNTIME_HELPER_CMD}} text search <file> --pattern "<pattern>" --json`, then read only the smallest bounded range with the platform file-reading tool instead of full-file Read. Before issuing a Read, ask yourself: "Have I read this file before, and has it changed since?" If the answer is "no, it hasn't changed" — do NOT read it. This applies to all files including those summarized in context-snapshot.md Section 4. Subagents (Critic, Reviewer) must receive context-snapshot.md and rely on it rather than independently re-reading the same files the orchestrator already read.
+3. **Never re-read unmodified files** — Once you have read a file into context, do NOT read it again unless it was modified by an Edit/Write operation after your last read. Use platform file/search tools for targeted lookup; when shell-free helper lookup is needed, run `{{RUNTIME_HELPER_CMD}} text search <file> --pattern "<pattern>" --json`, then read only the smallest bounded range with the platform file-reading tool instead of full-file Read. Before issuing a Read, ask yourself: "Have I read this file before, and has it changed since?" If the answer is "no, it hasn't changed" — do NOT read it. This applies to all files including those summarized in context-snapshot.md Section 4. Reviewer subagents must receive context-snapshot.md and rely on it rather than independently re-reading the same files the orchestrator already read.
 4. **Stay focused** — Do NOT explore code unrelated to this feature. No curiosity-driven reads.
 4. **One task at a time** — In Phase 4 (implement), complete and test one task before starting the next.
 5. **Minimize tool output** — Never load full command output into context. First capture command output to a temp file using the command/tool output option or the host-appropriate redirection, then inspect only the final relevant lines and use targeted search helpers to extract the information needed for the current task. Only read the filtered result — never the raw full output.
@@ -191,60 +191,6 @@ Do not spawn a top-level Reviewer subagent for planning analysis. Perform a boun
 
 **CP-2**: Plan self-check complete; no CRITICAL plan issues remain.
 
-{{IF_CRITIC_ENABLED}}
-### Phase 3.5: Plan Challenge — Critic Agent(s)
-
-**Guard**: Verify critic agent file exists before spawning:
-```bash
-{{RUNTIME_HELPER_CMD}} artifact exists {{CRITIC_SUBAGENT_PATH}} --exists-marker CRITIC:READY --missing-marker CRITIC:MISSING
-```
-If CRITIC:MISSING — skip Phase 3.5 entirely and proceed to Phase 4. Log: "Critic agent not installed — skipping Plan Challenge."
-
-**Choose ONE path based on `{{CRITIC_COUNT}}`:**
-
-**If {{CRITIC_COUNT}} = 1 → Single Critic** (skip to CP-2.5 after this):
-
-Spawn Critic agent (Agent tool, subagent_type="prizm-dev-team-critic", mode="plan", run_in_background=false, isolation=default/no worktree). Do not request worktree isolation; this prevents AI tool-created `.claude/worktrees/...` subagent worktrees. PrizmKit pipeline-managed linked git worktrees under `.prizmkit/state/worktrees/...` are separate and controlled by `USE_WORKTREE`.
-
-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**
-> 1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` FIRST — Section 3 has TRAPS/RULES, Section 4 has file manifest.
-> 2. Use context-snapshot.md as the shared source of truth. Do not create or enter AI tool-created `.claude/worktrees/...` subagent worktrees; use default/no worktree isolation and do not request worktree isolation.
-> 3. PrizmKit pipeline-managed linked git worktrees under `.prizmkit/state/worktrees/...` are a separate runner feature controlled by `USE_WORKTREE`; do not confuse them with AI tool-created `.claude/worktrees/...`.
-> 4. Read additional `.prizmkit/prizm-docs/` or source excerpts only when needed to verify a specific challenge.
-> 5. Challenge plan.md against the project's existing architecture, patterns, and style.
-> Write `.prizmkit/specs/{{FEATURE_SLUG}}/challenge-report.md` with findings (or 'No significant challenges')."
-
-**If {{CRITIC_COUNT}} = 3 → Multi-Critic Voting** (skip Single Critic above):
-
-**IMPORTANT**: Spawn all 3 Critics in PARALLEL (issue all 3 Agent tool calls in the SAME message turn). Do NOT wait for one before spawning the next.
-
-Spawn Critic-A, Critic-B, Critic-C simultaneously (each with mode="plan", run_in_background=false, isolation=default/no worktree). Do not request worktree isolation; this prevents AI tool-created `.claude/worktrees/...` subagent worktrees. PrizmKit pipeline-managed linked git worktrees under `.prizmkit/state/worktrees/...` are separate and controlled by `USE_WORKTREE`:
-
-Critic-A prompt (append to base prompt above):
-> "**Focus Lens: Architecture & Scalability.** Prioritize: architectural pattern fit, scalability implications, over-engineering risks, component boundary design.
-> Write `.prizmkit/specs/{{FEATURE_SLUG}}/challenge-report-A.md`."
-
-Critic-B prompt (append to base prompt above):
-> "**Focus Lens: Data Model & Edge Cases.** Prioritize: data model design fit, entity relationships, edge cases in business logic, missing boundary conditions.
-> Write `.prizmkit/specs/{{FEATURE_SLUG}}/challenge-report-B.md`."
-
-Critic-C prompt (append to base prompt above):
-> "**Focus Lens: Security & Performance.** Prioritize: security attack surface, authentication/authorization gaps, performance bottlenecks, resource leaks.
-> Write `.prizmkit/specs/{{FEATURE_SLUG}}/challenge-report-C.md`."
-
-Spawn failure cap: for team/config/lock errors, each Critic retries at most once. If 2 or more Critics fail to spawn after retry, perform the plan challenge inline and record the fallback.
-
-After all critics return, read all 3 reports:
-- Challenge raised by **2/3 or more** critics → **must respond** (adjust plan or justify why not)
-- Challenge raised by **1/3 only** → logged in context-snapshot but not blocking
-- Max 1 plan revision round.
-
-**CP-2.5**: Plan challenges reviewed and resolved.
-{{END_IF_CRITIC_ENABLED}}
 
 ### Implement — Orchestrator Direct (no Dev subagent)
 
@@ -265,7 +211,7 @@ Before starting, check plan.md Tasks:
 - Implements task-by-task, marking each `[x]` immediately
 - Creates/updates L2 `.prizm` docs when creating new modules
 - Defers scoped/full test execution until after the code-review loop completes
-- Preserves Reviewer/Critic behavior; only the top-level implementation Dev handoff is removed
+- Preserves Reviewer behavior; only the top-level implementation Dev handoff is removed
 - If plan.md has >5 tasks: update checkpoints after every 3 tasks
 
 **3b. Focused checks only (no test gate here)**:
@@ -295,7 +241,7 @@ For each Verification Gate from the Task Contract, write one evidence line to Im
 
 Review the completed implementation before the scoped feature test gate runs. Use `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/` so the code-review skill can read spec, plan, context snapshot, implementation log, and current diff artifacts. Do not require or read a prior `/prizmkit-test` report here; test generation and test-fix looping happen in the next phase.
 
-Run `/prizmkit-code-review` with `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/`.
+Run `/prizmkit-code-review` with `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/`. The code-review skill must launch Reviewer in `current-workspace / active-checkout / no-worktree` mode so it reviews the active checkout rather than an isolated copy; do not request worktree isolation or use `.claude/worktrees/...` / `.prizmkit/state/worktrees/...`. Do not set `USE_WORKTREE` for reviewer launches.
 
 The skill runs an internal review-fix loop (Reviewer Agent → filter → orchestrator fix, max 3 rounds) and writes `review-report.md` to the artifact directory.
 
@@ -562,9 +508,6 @@ Rules for writing completion notes:
 | Feature Artifacts Dir | `.prizmkit/specs/{{FEATURE_SLUG}}/` |
 | Context Snapshot | `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` |
 | Team Config | `{{TEAM_CONFIG_PATH}}` |
-{{IF_CRITIC_ENABLED}}
-| Critic Agent Def | {{CRITIC_SUBAGENT_PATH}} |
-{{END_IF_CRITIC_ENABLED}}
 | Project Root | {{PROJECT_ROOT}} |
 | Feature List Path | {{FEATURE_LIST_PATH}} |
 
@@ -587,10 +530,10 @@ If you encounter an unrecoverable error, context overflow, or are about to exit
 
 ## Reminders
 
-- Tier 3: orchestrator implements directly; Critic challenges plan; `/prizmkit-code-review` handles review later
+- Tier 3: orchestrator implements directly; `/prizmkit-code-review` handles review later
 - context-snapshot.md is append-only: orchestrator writes Sections 1-4 + Implementation Log, Reviewer appends Review Notes
 - Gate checks enforce Implementation Log and Review Notes are written before proceeding
-- Do NOT use `run_in_background=true` when spawning Critic agents
+- Do NOT use `run_in_background=true` when spawning Reviewer agents
 - Commit phase must use `/prizmkit-committer`; do NOT replace with manual git commit commands
 - **NEVER delete, modify, or touch any file under `.prizmkit/state/`** — those are pipeline runtime files managed by the runner
 - NEVER run `rm -rf`, `git clean`, or any destructive filesystem operations

package/bundled/dev-pipeline/templates/bug-fix-list-schema.json

@@ -181,22 +181,11 @@
             ],
             "description": "Bug fix status. Subset of feature status enum plus needs_info."
           },
-          "critic": {
-            "type": "boolean",
-            "description": "Enable adversarial plan challenge before implementation. Default: true for high severity bugs, false for others.",
-            "default": false
-          },
-          "critic_count": {
-            "type": "integer",
-            "description": "Number of parallel critic agents. 1 = single critic, 3 = multi-critic voting. Default: 1 for high severity, omit for others.",
-            "enum": [
-              1,
-              3
-            ]
-          },
           "user_context": {
             "type": "array",
-            "items": { "type": "string" },
+            "items": {
+              "type": "string"
+            },
             "description": "User-provided supplementary materials, preserved verbatim. Each entry is either inline content/rules (stored as-is) or a file reference (e.g. 'src/auth/login.ts:42-78', 'src/utils/ — focus on validation logic')."
           },
           "model": {
@@ -209,7 +198,11 @@
             "properties": {
               "tool": {
                 "type": "string",
-                "enum": ["playwright-cli", "opencli", "auto"],
+                "enum": [
+                  "playwright-cli",
+                  "opencli",
+                  "auto"
+                ],
                 "default": "auto",
                 "description": "Browser tool to use. 'auto' (default) = AI chooses at runtime. 'playwright-cli' = local dev server verification in isolated browser. 'opencli' = reuses Chrome logged-in session, ideal for verifying bugs related to third-party integrations or OAuth flows."
               },
@@ -222,7 +215,8 @@
               }
             }
           }
-        }
+        },
+        "additionalProperties": false
       }
     },
     "global_context": {