prizmkit 1.0.58 → 1.0.66

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

@@ -18,7 +18,7 @@ You are the **bug fix session orchestrator**. Fix Bug {{BUG_ID}}: "{{BUG_TITLE}}
 
 **CRITICAL SESSION LIFECYCLE RULE**: You MUST NOT exit until ALL work is complete and session-status.json is written. When you spawn subagents, you MUST **wait for each to finish** (run_in_background=false) before proceeding. Do NOT spawn an agent in the background and exit — that kills the session.
 
-**MANDATORY TEAM REQUIREMENT**: You MUST use the `prizm-dev-team` multi-agent team. This is NON-NEGOTIABLE. All implementation and review work MUST be performed by the appropriate team agents (Dev, Reviewer). You are the orchestrator — handle coordination, planning, and commit phases directly.
+**MANDATORY TEAM REQUIREMENT**: You MUST use the `prizm-dev-team` agents (Dev + Reviewer). This is NON-NEGOTIABLE. All implementation and review work MUST be performed by the appropriate team agents (Dev, Reviewer). You are the orchestrator — handle coordination, planning, and commit phases directly.
 
 **BUG FIX DOCUMENTATION POLICY**: Bug fixes MUST NOT be recorded as new documentation entries:
 - Run `/prizmkit-retrospective` with structural sync only (Job 1) — skip knowledge injection unless a genuinely new TRAP was discovered
@@ -28,8 +28,7 @@ You are the **bug fix session orchestrator**. Fix Bug {{BUG_ID}}: "{{BUG_TITLE}}
 
 ### Team Definition Reference
 
-- **Source of truth**: `{{TEAM_CONFIG_PATH}}`
-- **Installed team config**: `{{TEAM_CONFIG_PATH}}`
+- **Team config**: `{{TEAM_CONFIG_PATH}}`
 
 ### Bug Description
 
@@ -74,16 +73,11 @@ You are the **bug fix session orchestrator**. Fix Bug {{BUG_ID}}: "{{BUG_TITLE}}
 
 ### Step 1: Initialize
 
-#### Team Setup: Reuse or Create
+#### Agent Setup
 
-1. **Check if a team already exists and can be reused**:
-   - Read the team config file at `{{TEAM_CONFIG_PATH}}`
-   - If valid, reuse it. Set `TEAM_REUSED=true`
-
-2. **If no reusable team**, create a new one:
-   - Reference `{{TEAM_CONFIG_PATH}}`
-   - Call `TeamCreate` with `team_name="prizm-dev-team-{{BUG_ID}}"` and `description="Fixing {{BUG_TITLE}}"`
-   - Set `TEAM_REUSED=false`
+Reference `{{TEAM_CONFIG_PATH}}` for agent definitions:
+- Dev: `{{DEV_SUBAGENT_PATH}}`
+- Reviewer: `{{REVIEWER_SUBAGENT_PATH}}`
 
 3. Create bug fix artifacts directory:
    ```bash
@@ -96,7 +90,7 @@ You are the **bug fix session orchestrator**. Fix Bug {{BUG_ID}}: "{{BUG_TITLE}}
 
 **Goal**: Classify the bug, identify scope and severity, check known issues, produce fix-plan.md.
 
-- Spawn Dev agent (Task tool, subagent_type="prizm-dev-team-dev", run_in_background=false)
+- Spawn Dev agent (Agent tool, subagent_type="prizm-dev-team-dev", run_in_background=false)
   Prompt: "Read {{DEV_SUBAGENT_PATH}}. For bug {{BUG_ID}} ('{{BUG_TITLE}}'):
   1. Run `/prizmkit-tool-error-triage` with the bug description and error source
   2. Check `.prizm-docs/` TRAPS sections for matching known issues
@@ -133,7 +127,7 @@ You are the **bug fix session orchestrator**. Fix Bug {{BUG_ID}}: "{{BUG_TITLE}}
 
 **Goal**: Create an automated reproduction that proves the bug exists.
 
-- Spawn Dev agent (Task tool, subagent_type="prizm-dev-team-dev", run_in_background=false)
+- Spawn Dev agent (Agent tool, subagent_type="prizm-dev-team-dev", run_in_background=false)
   Prompt: "Read {{DEV_SUBAGENT_PATH}}. For bug {{BUG_ID}}:
   1. Read the fix plan from `.prizmkit/bugfix/{{BUG_ID}}/fix-plan.md`
   2. Run `/prizmkit-tool-bug-reproducer` with the bug description and triage results
@@ -155,7 +149,7 @@ You are the **bug fix session orchestrator**. Fix Bug {{BUG_ID}}: "{{BUG_TITLE}}
 
 **Goal**: Implement the fix. The reproduction test goes from red to green.
 
-- Spawn Dev agent (Task tool, subagent_type="prizm-dev-team-dev", run_in_background=false)
+- Spawn Dev agent (Agent tool, subagent_type="prizm-dev-team-dev", run_in_background=false)
   Prompt: "Read {{DEV_SUBAGENT_PATH}}. For bug {{BUG_ID}}:
   1. Read the fix plan from `.prizmkit/bugfix/{{BUG_ID}}/fix-plan.md`
   2. Read `.prizm-docs/` for affected modules (TRAPS, RULES, PATTERNS)
@@ -177,7 +171,7 @@ You are the **bug fix session orchestrator**. Fix Bug {{BUG_ID}}: "{{BUG_TITLE}}
 
 **Goal**: Ensure fix correctness and no regressions.
 
-- Spawn Reviewer agent (Task tool, subagent_type="prizm-dev-team-reviewer", run_in_background=false)
+- Spawn Reviewer agent (Agent tool, subagent_type="prizm-dev-team-reviewer", run_in_background=false)
   Prompt: "Read {{REVIEWER_SUBAGENT_PATH}}. For bug {{BUG_ID}}:
   1. Run `/prizmkit-code-review` scoped to CHANGED FILES ONLY
   2. Review dimensions (adjusted for bug fix):
@@ -206,17 +200,19 @@ You are the **bug fix session orchestrator**. Fix Bug {{BUG_ID}}: "{{BUG_TITLE}}
 
 **Goal**: Commit the fix, update TRAPS, generate fix-report.md.
 
-- Spawn Dev agent (Task tool, subagent_type="prizm-dev-team-dev", run_in_background=false)
-  Prompt: "Read {{DEV_SUBAGENT_PATH}}. For bug {{BUG_ID}}:
-  1. Run `/prizmkit-committer` with:
-     - Commit message: `fix({{FIX_SCOPE}}): {{BUG_TITLE}}`
-     - Include both fix code and reproduction test
-     - Do NOT run `/prizmkit-retrospective` with REGISTRY archiving
-     - Do NOT push (user will push manually)
-  2. If a new pitfall was discovered (not previously in TRAPS):
-     - Update the affected module's TRAPS section in `.prizm-docs/`
-     - Format: `- TRAP: <description> | FIX: <solution> | DATE: YYYY-MM-DD`
-  3. Write the complete fix report to `.prizmkit/bugfix/{{BUG_ID}}/fix-report.md`
+**This phase is executed by YOU (the orchestrator), NOT a subagent.**
+
+1. If a new pitfall was discovered (not previously in TRAPS):
+   - Update the affected module's TRAPS section in `.prizm-docs/`
+   - Format: `- TRAP: <description> | FIX: <solution> | DATE: YYYY-MM-DD`
+
+2. Run `/prizmkit-committer` with:
+   - Commit message: `fix({{FIX_SCOPE}}): {{BUG_TITLE}}`
+   - Include both fix code and reproduction test
+   - Do NOT run `/prizmkit-retrospective` with REGISTRY archiving
+   - Do NOT push (user will push manually)
+
+3. Write the complete fix report to `.prizmkit/bugfix/{{BUG_ID}}/fix-report.md`
 
   The fix-report.md MUST contain these sections:
   - Bug Resolution Summary (ID, title, status, phases completed, duration)
@@ -224,8 +220,7 @@ You are the **bug fix session orchestrator**. Fix Bug {{BUG_ID}}: "{{BUG_TITLE}}
   - Verification Results (reproduction test before/after, regression tests, review verdict)
   - Knowledge Captured (TRAPS updated, prevention recommendation)
   - Acceptance Criteria Verification (checklist with pass/fail for each criterion)
-  "
-- **Wait for Dev to return**
+
 - **CP-BF-5**: Commit recorded, fix-report.md written, TRAPS updated (if applicable)
 
 ### Step 3: Report Session Status
@@ -258,17 +253,11 @@ Write to: `{{SESSION_STATUS_PATH}}`
 
 **Status values**: `success` (all phases done) | `partial` (can resume) | `failed` (unrecoverable)
 
-### Step 4: Team Cleanup (conditional)
-
-**Only if you CREATED the team** (`TEAM_REUSED=false`), clean up with `TeamDelete`.
-**If you REUSED an existing team** (`TEAM_REUSED=true`), do NOT call `TeamDelete`.
-
 ## Critical Paths
 
 | Resource | Path |
 |----------|------|
 | Team Definition (source of truth) | `{{TEAM_CONFIG_PATH}}` |
-| Team Config (installed) | `{{TEAM_CONFIG_PATH}}` |
 | Bug Fix Artifacts Dir | `.prizmkit/bugfix/{{BUG_ID}}/` |
 | Fix Plan | `.prizmkit/bugfix/{{BUG_ID}}/fix-plan.md` |
 | Fix Report | `.prizmkit/bugfix/{{BUG_ID}}/fix-report.md` |
@@ -279,13 +268,12 @@ Write to: `{{SESSION_STATUS_PATH}}`
 
 ## Reminders
 
-- **MANDATORY**: Use `prizm-dev-team` — single-agent execution is FORBIDDEN
+- **MANDATORY**: Use `prizm-dev-team` agents — single-agent execution is FORBIDDEN
 - **Only 2 artifact files per bug**: fix-plan.md + fix-report.md — NEVER more
-- **Do NOT create** spec.md, plan.md, or tasks.md for bug fixes
+- **Do NOT create** spec.md or plan.md for bug fixes
 - **Do NOT run** `/prizmkit-retrospective` knowledge injection for bugs (structural sync only, unless genuinely new TRAP discovered)
 - **Commit with** `fix(<scope>):` prefix, NOT `feat:`
 - **Update TRAPS** in `.prizm-docs/` only if a genuinely new pitfall was discovered
 - Dev agents use TDD approach: reproduction test goes from RED → GREEN
 - ALWAYS write session-status.json before exiting
 - Do NOT use `run_in_background=true` when spawning agents
-- Only call `TeamDelete` if you created the team

package/bundled/dev-pipeline/templates/session-status-schema.json

@@ -72,7 +72,7 @@
       "properties": {
         "spec_path": { "type": "string" },
         "plan_path": { "type": "string" },
-        "tasks_path": { "type": "string" }
+        "context_snapshot_path": { "type": "string" }
       }
     },
     "timestamp": {

package/bundled/dev-pipeline/tests/conftest.py

@@ -9,13 +9,18 @@ import sys
 _scripts_dir = os.path.join(os.path.dirname(__file__), "..", "scripts")
 sys.path.insert(0, _scripts_dir)
 
-# generate-bootstrap-prompt.py has a hyphenated filename that Python can't
-# import normally.  Load it via importlib and register under an underscore name
-# so test files can do: `from generate_bootstrap_prompt import ...`
-_spec = importlib.util.spec_from_file_location(
-    "generate_bootstrap_prompt",
-    os.path.join(_scripts_dir, "generate-bootstrap-prompt.py"),
-)
-_mod = importlib.util.module_from_spec(_spec)
-sys.modules["generate_bootstrap_prompt"] = _mod
-_spec.loader.exec_module(_mod)
+
+def _load_hyphenated_module(module_name, filename):
+    """Load a hyphenated .py file and register it as an importable module."""
+    spec = importlib.util.spec_from_file_location(
+        module_name,
+        os.path.join(_scripts_dir, filename),
+    )
+    mod = importlib.util.module_from_spec(spec)
+    sys.modules[module_name] = mod
+    spec.loader.exec_module(mod)
+
+
+# Register hyphenated script files so tests can import them with underscores.
+_load_hyphenated_module("generate_bootstrap_prompt", "generate-bootstrap-prompt.py")
+_load_hyphenated_module("generate_bugfix_prompt", "generate-bugfix-prompt.py")

package/bundled/dev-pipeline/tests/test_generate_bugfix_prompt.py

@@ -0,0 +1,168 @@
+"""Tests for generate-bugfix-prompt.py core functions."""
+
+from generate_bugfix_prompt import (
+    find_bug,
+    format_acceptance_criteria,
+    format_global_context,
+    format_error_source_details,
+    format_environment,
+    process_conditional_blocks,
+    render_template,
+)
+
+
+# ---------------------------------------------------------------------------
+# find_bug
+# ---------------------------------------------------------------------------
+
+class TestFindBug:
+    def test_found(self):
+        bugs = [{"id": "B-001", "title": "A"}, {"id": "B-002", "title": "B"}]
+        assert find_bug(bugs, "B-002") == {"id": "B-002", "title": "B"}
+
+    def test_not_found(self):
+        assert find_bug([{"id": "B-001"}], "B-999") is None
+
+    def test_empty_list(self):
+        assert find_bug([], "B-001") is None
+
+    def test_non_dict_items(self):
+        assert find_bug(["garbage", 42, None, {"id": "B-001"}], "B-001") == {"id": "B-001"}
+
+
+# ---------------------------------------------------------------------------
+# format_error_source_details
+# ---------------------------------------------------------------------------
+
+class TestFormatErrorSourceDetails:
+    def test_none(self):
+        result = format_error_source_details(None)
+        assert "no error source" in result
+
+    def test_empty_dict(self):
+        result = format_error_source_details({})
+        assert "no error source" in result
+
+    def test_stack_trace(self):
+        source = {"type": "stack_trace", "stack_trace": "Error at line 42"}
+        result = format_error_source_details(source)
+        assert "Error at line 42" in result
+        assert "Stack Trace" in result
+
+    def test_error_message(self):
+        source = {"type": "unknown", "error_message": "Something went wrong"}
+        result = format_error_source_details(source)
+        assert "Something went wrong" in result
+
+    def test_log_pattern(self):
+        source = {"type": "log_pattern", "log_snippet": "FATAL: connection refused"}
+        result = format_error_source_details(source)
+        assert "connection refused" in result
+
+    def test_failed_test(self):
+        source = {"type": "failed_test", "failed_test_path": "tests/auth.test.js"}
+        result = format_error_source_details(source)
+        assert "tests/auth.test.js" in result
+
+    def test_user_report(self):
+        source = {"type": "user_report", "reproduction_steps": ["Click login", "Enter bad password"]}
+        result = format_error_source_details(source)
+        assert "Click login" in result
+        assert "Enter bad password" in result
+
+
+# ---------------------------------------------------------------------------
+# format_environment
+# ---------------------------------------------------------------------------
+
+class TestFormatEnvironment:
+    def test_none(self):
+        assert "not specified" in format_environment(None)
+
+    def test_empty(self):
+        assert "not specified" in format_environment({})
+
+    def test_with_values(self):
+        result = format_environment({"os": "Linux", "node": "20.1"})
+        assert "**node**: 20.1" in result
+        assert "**os**: Linux" in result
+
+    def test_skips_empty_values(self):
+        result = format_environment({"os": "Linux", "browser": ""})
+        assert "**os**: Linux" in result
+        assert "browser" not in result
+
+
+# ---------------------------------------------------------------------------
+# process_conditional_blocks
+# ---------------------------------------------------------------------------
+
+class TestProcessConditionalBlocks:
+    def test_automated_removes_manual_block(self):
+        tpl = "before\n{{IF_VERIFICATION_MANUAL_OR_HYBRID}}\nmanual content\n{{END_IF_VERIFICATION_MANUAL_OR_HYBRID}}\nafter"
+        bug = {"verification_type": "automated"}
+        result = process_conditional_blocks(tpl, bug)
+        assert "manual content" not in result
+        assert "before" in result
+        assert "after" in result
+
+    def test_manual_keeps_block(self):
+        tpl = "before\n{{IF_VERIFICATION_MANUAL_OR_HYBRID}}\nmanual content\n{{END_IF_VERIFICATION_MANUAL_OR_HYBRID}}\nafter"
+        bug = {"verification_type": "manual"}
+        result = process_conditional_blocks(tpl, bug)
+        assert "manual content" in result
+        assert "IF_VERIFICATION" not in result
+
+    def test_hybrid_keeps_block(self):
+        tpl = "{{IF_VERIFICATION_MANUAL_OR_HYBRID}}hybrid{{END_IF_VERIFICATION_MANUAL_OR_HYBRID}}"
+        bug = {"verification_type": "hybrid"}
+        result = process_conditional_blocks(tpl, bug)
+        assert "hybrid" in result
+
+    def test_default_is_automated(self):
+        tpl = "{{IF_VERIFICATION_MANUAL_OR_HYBRID}}content{{END_IF_VERIFICATION_MANUAL_OR_HYBRID}}"
+        bug = {}
+        result = process_conditional_blocks(tpl, bug)
+        assert "content" not in result
+
+
+# ---------------------------------------------------------------------------
+# render_template (integration)
+# ---------------------------------------------------------------------------
+
+class TestRenderTemplate:
+    def test_placeholders_replaced(self):
+        tpl = "Bug: {{BUG_ID}} — {{BUG_TITLE}}"
+        replacements = {"{{BUG_ID}}": "B-042", "{{BUG_TITLE}}": "Login crash"}
+        bug = {"verification_type": "automated"}
+        result = render_template(tpl, replacements, bug)
+        assert result == "Bug: B-042 — Login crash"
+
+    def test_conditional_and_replacement(self):
+        tpl = (
+            "{{IF_VERIFICATION_MANUAL_OR_HYBRID}}manual{{END_IF_VERIFICATION_MANUAL_OR_HYBRID}}"
+            "id={{BUG_ID}}"
+        )
+        replacements = {"{{BUG_ID}}": "B-001"}
+        bug = {"verification_type": "automated"}
+        result = render_template(tpl, replacements, bug)
+        assert "manual" not in result
+        assert "id=B-001" in result
+
+
+# ---------------------------------------------------------------------------
+# Reuse shared helpers (same as bootstrap prompt — verify they are present)
+# ---------------------------------------------------------------------------
+
+class TestSharedHelpers:
+    def test_format_acceptance_criteria_items(self):
+        result = format_acceptance_criteria(["Fix works", "No regression"])
+        assert "- Fix works" in result
+        assert "- No regression" in result
+
+    def test_format_acceptance_criteria_empty(self):
+        assert "none specified" in format_acceptance_criteria([])
+
+    def test_format_global_context_dict(self):
+        result = format_global_context({"lang": "Python"})
+        assert "**lang**: Python" in result

package/bundled/skills/_metadata.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.0.58",
+  "version": "1.0.66",
   "skills": {
     "prizm-kit": {
       "description": "Full-lifecycle dev toolkit. Covers spec-driven development, Prizm context docs, code quality, debugging, deployment, and knowledge management.",

package/bundled/skills/bug-fix-workflow/SKILL.md

@@ -112,15 +112,13 @@ If the fix causes test regressions:
 
 **Goal**: Commit the fix with proper conventions.
 
-1. **Run `/prizmkit-retrospective`** (Job 1: structural sync only):
-   - Update `.prizm-docs/` if file structure changed
-   - Add TRAPS entry only if a genuinely new pitfall was discovered
-   - Skip knowledge injection for routine bug fixes
-2. **Run `/prizmkit-committer`**:
+1. **Run `/prizmkit-committer`**:
    - Commit message: `fix(<scope>): <description>`
    - Include both fix code and reproduction test
    - Do NOT push (user decides when to push)
-3. **If bug came from bug-fix-list.json**: inform user to update bug status
+   - Do NOT run `/prizmkit-retrospective` — bug fixes do not update `.prizm-docs/` (per project rules: "bugs are incomplete features, recording bug details causes doc bloat with no AI value")
+   - `/prizmkit-committer` is a pure commit tool — it does NOT modify `.prizm-docs/` or any project files
+2. **If bug came from bug-fix-list.json**: inform user to update bug status
    ```
    Bug B-001 fixed and committed.
    To update the bug list: manually set B-001 status to "fixed" in bug-fix-list.json
@@ -163,7 +161,7 @@ Only 2 artifact files per bug, consistent with the pipeline convention.
 | `bug-planner` | **this skill** | User picks one bug to fix interactively |
 | `bugfix-pipeline-launcher` | **this skill** | User wants to fix a stuck/complex bug manually |
 | **this skill** | `bugfix-pipeline-launcher` | After fixing, user wants to continue with remaining bugs |
-| **this skill** | `prizmkit-retrospective` | Built into Phase 5 (structural sync) |
+| **this skill** | `prizmkit-committer` | Built into Phase 5 (pure commit, no doc sync) |
 
 ## Output
 
@@ -171,4 +169,3 @@ Only 2 artifact files per bug, consistent with the pipeline convention.
 - `.prizmkit/bugfix/<BUG_ID>/fix-plan.md`
 - `.prizmkit/bugfix/<BUG_ID>/fix-report.md`
 - Git commit with `fix(<scope>):` prefix
-- Updated `.prizm-docs/` TRAPS (if new pitfall discovered)

package/bundled/skills/bug-planner/SKILL.md

@@ -135,7 +135,11 @@ ALERT: Error rate spike: 500 errors/min on /api/login endpoint
 ### Phase 4: Generate & Validate
 
 1. **Generate `bug-fix-list.json`**: Conform to `dev-pipeline/templates/bug-fix-list-schema.json`
-2. **Validate against schema**: Run the validation checks below
+2. **Validate against schema**: Run the validation script:
+   ```bash
+   python3 ${SKILL_DIR}/scripts/validate-bug-list.py bug-fix-list.json --feature-list feature-list.json
+   ```
+   If the script is not available, perform the validation checks manually (see checklist below).
 3. **Write file** to project root (or user-specified path)
 4. **Output**: File path, summary, and next steps
 

package/bundled/skills/bug-planner/scripts/validate-bug-list.py

@@ -0,0 +1,156 @@
+#!/usr/bin/env python3
+"""
+Validate bug-fix-list.json against the PrizmKit bug-fix-list schema.
+
+Usage:
+    python3 validate-bug-list.py [bug-fix-list.json] [--feature-list feature-list.json]
+
+Exit codes:
+    0 = valid
+    1 = validation errors found
+    2 = file not found or JSON parse error
+"""
+
+import json
+import sys
+import os
+import re
+
+VALID_SEVERITIES = {"critical", "high", "medium", "low"}
+VALID_SOURCE_TYPES = {"stack_trace", "user_report", "failed_test", "log_pattern", "monitoring_alert"}
+VALID_VERIFICATION_TYPES = {"automated", "manual", "hybrid"}
+VALID_STATUSES = {"pending", "in_progress", "fixed", "failed", "skipped", "needs_info"}
+BUG_ID_PATTERN = re.compile(r"^B-\d{3}$")
+
+
+def validate(bug_list_path, feature_list_path=None):
+    errors = []
+    warnings = []
+
+    # Load bug-fix-list.json
+    try:
+        with open(bug_list_path) as f:
+            data = json.load(f)
+    except FileNotFoundError:
+        print(f"ERROR: File not found: {bug_list_path}", file=sys.stderr)
+        return 2
+    except json.JSONDecodeError as e:
+        print(f"ERROR: Invalid JSON in {bug_list_path}: {e}", file=sys.stderr)
+        return 2
+
+    # Load feature-list.json (optional, for cross-reference)
+    feature_ids = set()
+    if feature_list_path:
+        try:
+            with open(feature_list_path) as f:
+                fl_data = json.load(f)
+            feature_ids = {f.get("id") for f in fl_data.get("features", [])}
+        except (FileNotFoundError, json.JSONDecodeError):
+            warnings.append(f"Could not load feature-list.json at {feature_list_path}")
+
+    # Top-level required fields
+    if "$schema" not in data:
+        errors.append("Missing required field: $schema")
+    elif data["$schema"] != "dev-pipeline-bug-fix-list-v1":
+        errors.append(f"Invalid $schema: expected 'dev-pipeline-bug-fix-list-v1', got '{data['$schema']}'")
+
+    if not data.get("project_name"):
+        errors.append("Missing or empty required field: project_name")
+
+    bugs = data.get("bugs", [])
+    if not bugs:
+        errors.append("Missing or empty required field: bugs")
+
+    # Per-bug validation
+    seen_ids = set()
+    seen_priorities = set()
+
+    for i, bug in enumerate(bugs):
+        prefix = f"bugs[{i}]"
+
+        # Required fields
+        bug_id = bug.get("id", "")
+        if not bug_id:
+            errors.append(f"{prefix}: missing required field 'id'")
+        elif not BUG_ID_PATTERN.match(bug_id):
+            errors.append(f"{prefix}: id '{bug_id}' does not match pattern B-NNN")
+
+        if bug_id in seen_ids:
+            errors.append(f"{prefix}: duplicate bug id '{bug_id}'")
+        seen_ids.add(bug_id)
+
+        if not bug.get("title"):
+            errors.append(f"{prefix} ({bug_id}): missing required field 'title'")
+
+        if not bug.get("description"):
+            errors.append(f"{prefix} ({bug_id}): missing required field 'description'")
+
+        severity = bug.get("severity", "")
+        if severity not in VALID_SEVERITIES:
+            errors.append(f"{prefix} ({bug_id}): invalid severity '{severity}' — must be one of {VALID_SEVERITIES}")
+
+        # error_source
+        error_source = bug.get("error_source", {})
+        source_type = error_source.get("type", "") if isinstance(error_source, dict) else ""
+        if source_type not in VALID_SOURCE_TYPES:
+            errors.append(f"{prefix} ({bug_id}): invalid error_source.type '{source_type}' — must be one of {VALID_SOURCE_TYPES}")
+
+        # verification_type
+        vtype = bug.get("verification_type", "")
+        if vtype not in VALID_VERIFICATION_TYPES:
+            errors.append(f"{prefix} ({bug_id}): invalid verification_type '{vtype}' — must be one of {VALID_VERIFICATION_TYPES}")
+
+        # acceptance_criteria
+        ac = bug.get("acceptance_criteria", [])
+        if not ac or not isinstance(ac, list):
+            errors.append(f"{prefix} ({bug_id}): missing or empty acceptance_criteria array")
+
+        # status
+        status = bug.get("status", "")
+        if status not in VALID_STATUSES:
+            errors.append(f"{prefix} ({bug_id}): invalid status '{status}' — must be one of {VALID_STATUSES}")
+
+        # Priority uniqueness
+        priority = bug.get("priority")
+        if priority is not None:
+            if priority in seen_priorities:
+                warnings.append(f"{prefix} ({bug_id}): duplicate priority {priority}")
+            seen_priorities.add(priority)
+
+        # Cross-reference affected_feature
+        affected_feature = bug.get("affected_feature")
+        if affected_feature and feature_ids and affected_feature not in feature_ids:
+            warnings.append(f"{prefix} ({bug_id}): affected_feature '{affected_feature}' not found in feature-list.json")
+
+    # Output results
+    if errors:
+        print(f"VALIDATION FAILED — {len(errors)} error(s), {len(warnings)} warning(s)\n")
+        for e in errors:
+            print(f"  ERROR: {e}")
+        for w in warnings:
+            print(f"  WARN:  {w}")
+        return 1
+    else:
+        bug_count = len(bugs)
+        severity_counts = {}
+        for b in bugs:
+            s = b.get("severity", "unknown")
+            severity_counts[s] = severity_counts.get(s, 0) + 1
+        sev_str = ", ".join(f"{k}={v}" for k, v in sorted(severity_counts.items()))
+        print(f"VALIDATION PASSED — {bug_count} bugs ({sev_str})")
+        if warnings:
+            for w in warnings:
+                print(f"  WARN:  {w}")
+        return 0
+
+
+if __name__ == "__main__":
+    bug_list = sys.argv[1] if len(sys.argv) > 1 else "bug-fix-list.json"
+    feature_list = None
+
+    if "--feature-list" in sys.argv:
+        idx = sys.argv.index("--feature-list")
+        if idx + 1 < len(sys.argv):
+            feature_list = sys.argv[idx + 1]
+
+    sys.exit(validate(bug_list, feature_list))

package/bundled/skills/bugfix-pipeline-launcher/SKILL.md

@@ -5,11 +5,11 @@ description: "Launch and manage the bugfix pipeline from within an AI CLI sessio
 
 # Bugfix-Pipeline Launcher
 
-Launch the autonomous bug fix pipeline from within a cbc conversation. The pipeline runs as a fully detached background process -- closing the cbc session does NOT stop the pipeline.
+Launch the autonomous bug fix pipeline from within an AI CLI conversation. The pipeline runs as a fully detached background process -- closing the AI CLI session does NOT stop the pipeline.
 
 ### Execution Mode
 
-Always use daemon mode via `dev-pipeline/launch-bugfix-daemon.sh` for start/stop/status/log actions. Foreground `run-bugfix.sh` can be terminated by AI CLI command timeout (e.g. cbc 120s), while daemon mode survives session timeout — this prevents half-finished bug fixes that leave the codebase in an inconsistent state.
+Always use daemon mode via `dev-pipeline/launch-bugfix-daemon.sh` for start/stop/status/log actions. Foreground `run-bugfix.sh` can be terminated by AI CLI command timeout, while daemon mode survives session timeout — this prevents half-finished bug fixes that leave the codebase in an inconsistent state.
 
 ### When to Use
 
@@ -246,7 +246,7 @@ SESSION_TIMEOUT=3600 dev-pipeline/retry-bug.sh B-001 bug-fix-list.json
 ### Integration Notes
 
 - **After bug-planner**: This is the natural next step. When user finishes bug planning and has `bug-fix-list.json`, suggest launching the bugfix pipeline.
-- **Session independence**: The bugfix pipeline runs completely detached. User can close cbc, open a new session later, and use this skill to check progress or stop the pipeline.
+- **Session independence**: The bugfix pipeline runs completely detached. User can close the AI CLI, open a new session later, and use this skill to check progress or stop the pipeline.
 - **Single instance**: Only one bugfix pipeline can run at a time. The PID file prevents duplicates.
 - **Feature pipeline coexistence**: Bugfix and feature pipelines use separate state directories (`bugfix-state/` vs `state/`), so they can run simultaneously without conflict.
 - **State preservation**: Stopping and restarting the bugfix pipeline resumes from where it left off -- completed bugs are not re-fixed.

package/bundled/skills/dev-pipeline-launcher/SKILL.md

@@ -9,7 +9,7 @@ Launch the autonomous development pipeline from within an AI CLI conversation. T
 
 ### Execution Mode
 
-Always use daemon mode via `dev-pipeline/launch-daemon.sh` for start/stop/status/log actions. Foreground `run.sh` can be terminated by AI CLI command timeout (e.g. cbc 120s, claude may vary), while daemon mode survives session timeout — this prevents half-finished features that leave the codebase in an inconsistent state.
+Always use daemon mode via `dev-pipeline/launch-daemon.sh` for start/stop/status/log actions. Foreground `run.sh` can be terminated by AI CLI session timeout, while daemon mode survives session closure — this prevents half-finished features that leave the codebase in an inconsistent state.
 
 ### When to Use
 

package/bundled/skills/prizm-kit/SKILL.md

@@ -27,16 +27,16 @@ PrizmKit is a comprehensive, independent AI development toolkit that covers the
 
 The full workflow generates spec, plan, and task artifacts that create a traceable record of what was built and why — this matters for future maintainability and AI context loading.
 
-**Use fast path (implement -> commit directly):**
+**Use fast path (plan → implement → commit):**
 - Bug fixes with clear root cause
 - Single-file config or typo fixes
 - Simple refactors (rename, extract)
 - Documentation-only changes
 - Test additions for existing code
 
-The fast path skips artifact generation because these changes don't introduce new concepts that future sessions need to understand.
+The fast path skips specify and analyze but still generates a simplified plan.md (with Tasks section) so that implement has a task list to follow.
 
-For fast-path changes, you can directly use the implement command with inline task description, then the commit command.
+For fast-path changes, you can directly generate a simplified plan.md, then use implement and commit commands.
 
 ## Workflow Example
 
@@ -47,17 +47,19 @@ For fast-path changes, you can directly use the implement command with inline ta
 /prizmkit-analyze    → checks spec↔plan consistency, finds gaps
 /prizmkit-implement  → executes tasks in order, marks [x] as done
 /prizmkit-code-review → reviews against spec, outputs PASS/NEEDS FIXES
-/prizmkit-committer  → updates .prizm-docs/, commits feat(avatar): add upload
+/prizmkit-retrospective → syncs .prizm-docs/ with code changes
+/prizmkit-committer  → commits feat(avatar): add upload
 ```
 
 **Fast path** for fixing a null pointer bug:
 ```
-/prizmkit-implement  → "fix null check in UserService.getAvatar()"
+/prizmkit-plan       → "fix null check in UserService.getAvatar()" (simplified plan.md)
+/prizmkit-implement  → executes tasks from plan.md
 /prizmkit-committer  → commits fix(user): handle null avatar gracefully
 ```
 
 ### Fast Path Commands
- `/prizmkit-implement` → `/prizmkit-committer`
+ `/prizmkit-plan` → `/prizmkit-implement` → `/prizmkit-committer`
 
 ### Bug Fix Documentation Policy
 
@@ -140,7 +142,7 @@ Not sure which skill to use? Follow this:
 | Fix one specific bug right now, interactively | `bug-fix-workflow` |
 | Refactor/restructure code without changing behavior | `refactor-workflow` |
 | Add a single small feature (spec → plan → implement) | `/prizmkit-specify` → `/prizmkit-plan` → `/prizmkit-implement` |
-| Quick bug fix or config change | Fast path: `/prizmkit-implement` → `/prizmkit-committer` |
+| Quick bug fix or config change | Fast path: `/prizmkit-plan` → `/prizmkit-implement` → `/prizmkit-committer` |
 
 ### Tier Definitions