prizmkit 1.1.86 → 1.1.88

package/bundled/dev-pipeline/scripts/prizmkit-test-gate.py

@@ -0,0 +1,446 @@
+#!/usr/bin/env python3
+"""Scoped PrizmKit test gate for feature pipeline prompts.
+
+The feature bootstrap prompt calls this script instead of embedding the full
+Bash/PowerShell report validation logic inline.  It intentionally prints compact
+`GATE:*` lines so the AI session can decide whether to continue, retry, or stop.
+"""
+
+import argparse
+import os
+import subprocess
+import sys
+from pathlib import Path
+
+REQUIRED_BOUNDARY_COLUMNS = [
+    "Module",
+    "Interface",
+    "Service Type",
+    "Happy Path",
+    "Request Validation",
+    "Auth / Permission / Ownership",
+    "Domain Invariants",
+    "Collection / Pagination",
+    "Date / Time",
+    "State Transitions",
+    "Dependency Failure",
+    "Response Contract",
+    "N/A Reasons",
+    "Final Status",
+]
+
+BOUNDARY_VALIDATOR_CANDIDATES = [
+    ".claude/command-assets/prizmkit-test/scripts/validate_boundary_report.py",
+    ".codebuddy/skills/prizmkit-test/scripts/validate_boundary_report.py",
+    ".agents/skills/prizmkit-test/scripts/validate_boundary_report.py",
+]
+
+OPENAPI_CANDIDATES = [
+    "openapi.yaml",
+    "openapi.yml",
+    "swagger.yaml",
+    "swagger.yml",
+    "docs/openapi.yaml",
+    "docs/openapi.yml",
+    "docs/swagger.yaml",
+    "docs/swagger.yml",
+    "api/openapi.yaml",
+    "api/openapi.yml",
+    "api/swagger.yaml",
+    "api/swagger.yml",
+]
+
+IGNORED_SCOPE_VALUES = {"none", "n/a", "not applicable", "(none)", "{...}", "..."}
+
+
+def default_artifact_dir(feature_slug):
+    return ".prizmkit/specs/{}/".format(feature_slug)
+
+
+def marker_path(feature_slug):
+    return os.path.join(default_artifact_dir(feature_slug), ".prizmkit-test-started")
+
+
+def pointer_path(feature_slug):
+    return os.path.join(default_artifact_dir(feature_slug), "test-report-path.txt")
+
+
+def normalize_artifact_dir(path):
+    return str(path or "").strip().replace("\\", "/").rstrip("/")
+
+
+def read_text(path):
+    with open(path, "r", encoding="utf-8") as fh:
+        return fh.read()
+
+
+def start_gate(feature_slug):
+    marker = marker_path(feature_slug)
+    os.makedirs(os.path.dirname(marker), exist_ok=True)
+    Path(marker).touch()
+    return {"gate": "GATE:START", "marker": marker}
+
+
+def newest_report_after_marker(marker):
+    if not os.path.isfile(marker):
+        return ""
+    try:
+        marker_mtime = os.path.getmtime(marker)
+    except OSError:
+        return ""
+
+    matches = []
+    for root, _dirs, files in os.walk(os.path.join(".prizmkit", "test")):
+        if "test-report.md" not in files:
+            continue
+        path = os.path.join(root, "test-report.md")
+        try:
+            report_mtime = os.path.getmtime(path)
+        except OSError:
+            continue
+        if report_mtime >= marker_mtime:
+            matches.append((report_mtime, path))
+
+    if not matches:
+        return ""
+    return sorted(matches)[-1][1]
+
+
+def extract_section(report_text, heading):
+    in_section = False
+    lines = []
+    for raw_line in report_text.splitlines():
+        line = raw_line.strip()
+        if line == heading:
+            in_section = True
+            continue
+        if in_section and line.startswith("## "):
+            break
+        if in_section:
+            lines.append(raw_line)
+    return lines
+
+
+def extract_scope_field(report_text, field_name):
+    prefix = "- {}:".format(field_name)
+    for raw_line in extract_section(report_text, "## Scope"):
+        line = raw_line.strip()
+        if line.startswith(prefix):
+            return line[len(prefix):].strip()
+    return ""
+
+
+def extract_verdict(report_text):
+    for raw_line in extract_section(report_text, "## Verdict"):
+        line = raw_line.strip()
+        if line:
+            return line
+    return ""
+
+
+def extract_key_value(section_lines, field_name):
+    prefix = "{}:".format(field_name).lower()
+    for raw_line in section_lines:
+        line = raw_line.strip()
+        if line.startswith("-"):
+            line = line[1:].strip()
+        if line.lower().startswith(prefix):
+            return line[len(prefix):].strip()
+    return ""
+
+
+def parse_markdown_cells(line):
+    stripped = line.strip()
+    if not stripped.startswith("|"):
+        return []
+    return [cell.strip() for cell in stripped.strip("|").split("|")]
+
+
+def boundary_columns_ok(matrix_lines):
+    for line in matrix_lines:
+        cells = parse_markdown_cells(line)
+        if cells and all(column in cells for column in REQUIRED_BOUNDARY_COLUMNS):
+            return True
+    return False
+
+
+def boundary_incomplete(matrix_lines):
+    text = "\n".join(matrix_lines).lower()
+    return any(token in text for token in ["boundary-missing", "happy-path-only", "unresolved"])
+
+
+def discover_openapi_file():
+    for candidate in OPENAPI_CANDIDATES:
+        if os.path.isfile(candidate):
+            return candidate
+    return ""
+
+
+def boundary_validator_passed(report_path, openapi_file):
+    for validator in BOUNDARY_VALIDATOR_CANDIDATES:
+        if not os.path.isfile(validator):
+            continue
+        args = [sys.executable, validator, "--report", report_path]
+        if openapi_file:
+            args.extend(["--openapi", openapi_file])
+        result = subprocess.run(
+            args,
+            stdout=subprocess.DEVNULL,
+            stderr=subprocess.DEVNULL,
+            check=False,
+        )
+        if result.returncode == 0:
+            return True
+    return False
+
+
+def scope_list(report_text, name):
+    values = []
+    in_list = False
+    marker = "- {}:".format(name)
+    for raw_line in extract_section(report_text, "## Scope"):
+        line = raw_line.strip()
+        if line == marker:
+            in_list = True
+            continue
+        if not in_list:
+            continue
+        if raw_line.startswith("  -") or raw_line.startswith("\t-"):
+            value = line[2:].strip().strip("`")
+            if value and value not in {"{...}", "..."}:
+                values.append(value)
+            continue
+        if line.startswith("- "):
+            break
+    return values
+
+
+def path_is_inside_project(project_root, candidate):
+    try:
+        return os.path.commonpath([project_root, candidate]) == project_root
+    except ValueError:
+        return False
+
+
+def scope_fresh_ok(report_path, marker, report_text):
+    try:
+        report_mtime = os.path.getmtime(report_path)
+        marker_mtime = os.path.getmtime(marker)
+    except OSError:
+        return False
+    if report_mtime < marker_mtime:
+        return False
+
+    source_files = scope_list(report_text, "In-Scope Source Files")
+    test_files = scope_list(report_text, "In-Scope Test Files")
+    if not source_files or not test_files:
+        return False
+
+    project_root = os.path.realpath(os.getcwd())
+    for listed_file in source_files + test_files:
+        normalized = listed_file.strip().strip("`")
+        if not normalized or normalized.lower() in IGNORED_SCOPE_VALUES:
+            return False
+        candidate = normalized if os.path.isabs(normalized) else os.path.join(os.getcwd(), normalized)
+        candidate_real = os.path.realpath(candidate)
+        if not path_is_inside_project(project_root, candidate_real):
+            return False
+        if not os.path.isfile(candidate_real):
+            return False
+        if os.path.getmtime(candidate_real) > report_mtime:
+            return False
+    return True
+
+
+def write_report_pointer(feature_slug, report_path):
+    path = pointer_path(feature_slug)
+    os.makedirs(os.path.dirname(path), exist_ok=True)
+    with open(path, "w", encoding="utf-8") as fh:
+        fh.write(report_path + "\n")
+    return path
+
+
+def update_checkpoint(checkpoint_path):
+    script_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "update-checkpoint.py")
+    if not checkpoint_path:
+        return True, ""
+    result = subprocess.run(
+        [
+            sys.executable,
+            script_path,
+            "--checkpoint-path",
+            checkpoint_path,
+            "--step",
+            "prizmkit-test",
+            "--status",
+            "completed",
+        ],
+        stdout=subprocess.PIPE,
+        stderr=subprocess.STDOUT,
+        text=True,
+        check=False,
+    )
+    if result.returncode == 0:
+        return True, ""
+    output = " ".join((result.stdout or "").split())
+    return False, output[:500]
+
+
+def validate_report(report_path, marker, feature_slug, expected_artifact_dir):
+    try:
+        report_text = read_text(report_path)
+    except OSError as exc:
+        return {
+            "status": "FAIL",
+            "reason": "unreadable_report",
+            "error": str(exc),
+            "report": report_path,
+        }
+
+    report_mode = extract_scope_field(report_text, "Mode")
+    report_artifact_dir = extract_scope_field(report_text, "Artifact Dir")
+    report_verdict = extract_verdict(report_text)
+
+    boundary_gate = extract_section(report_text, "## Boundary Completion Gate")
+    boundary_matrix = extract_section(report_text, "## Boundary Matrix")
+    boundary_validation = extract_section(report_text, "## Boundary Validation")
+
+    gate_passed = extract_key_value(boundary_gate, "Completion gate passed")
+    boundary_missing = extract_key_value(boundary_gate, "Boundary-missing")
+    happy_path_only = extract_key_value(boundary_gate, "Happy-path-only")
+    validation_result = extract_key_value(boundary_validation, "Validator result").lower()
+
+    columns_ok = boundary_columns_ok(boundary_matrix)
+    incomplete = boundary_incomplete(boundary_matrix)
+    openapi_file = discover_openapi_file()
+    validator_ok = boundary_validator_passed(report_path, openapi_file)
+    fresh_ok = scope_fresh_ok(report_path, marker, report_text)
+
+    artifact_ok = normalize_artifact_dir(report_artifact_dir) == normalize_artifact_dir(expected_artifact_dir)
+    boundary_ok = (
+        columns_ok
+        and not incomplete
+        and gate_passed == "yes"
+        and boundary_missing == "0"
+        and happy_path_only == "0"
+        and validation_result == "passed"
+        and validator_ok
+        and fresh_ok
+    )
+
+    result = {
+        "status": "PASS" if report_mode == "this-change" and artifact_ok and report_verdict == "PASS" and boundary_ok else "FAIL",
+        "verdict": report_verdict,
+        "mode": report_mode,
+        "artifact_dir": report_artifact_dir,
+        "boundary_gate": gate_passed,
+        "boundary_missing": boundary_missing,
+        "happy_path_only": happy_path_only,
+        "boundary_validation": validation_result,
+        "validator_passed": "1" if validator_ok else "0",
+        "scope_fresh": "1" if fresh_ok else "0",
+        "openapi": openapi_file,
+        "report": report_path,
+        "feature_slug": feature_slug,
+    }
+    if not columns_ok:
+        result["reason"] = "boundary_columns_missing"
+    elif incomplete:
+        result["reason"] = "boundary_incomplete"
+    elif not fresh_ok:
+        result["reason"] = "scope_not_fresh"
+    elif not artifact_ok:
+        result["reason"] = "wrong_artifact_dir"
+    elif report_mode != "this-change":
+        result["reason"] = "wrong_mode"
+    elif report_verdict != "PASS":
+        result["reason"] = "verdict_not_pass"
+    elif not validator_ok:
+        result["reason"] = "validator_failed"
+    elif not boundary_ok:
+        result["reason"] = "boundary_gate_failed"
+    return result
+
+
+def check_gate(feature_slug, artifact_dir=None, checkpoint_path=None):
+    expected_artifact_dir = artifact_dir or default_artifact_dir(feature_slug)
+    marker = marker_path(feature_slug)
+    report_path = newest_report_after_marker(marker)
+    if not report_path:
+        return {"status": "MISSING", "marker": marker}
+
+    result = validate_report(report_path, marker, feature_slug, expected_artifact_dir)
+    if result["status"] != "PASS":
+        return result
+
+    write_report_pointer(feature_slug, report_path)
+    checkpoint_ok, checkpoint_error = update_checkpoint(checkpoint_path)
+    if not checkpoint_ok:
+        result["status"] = "FAIL"
+        result["reason"] = "checkpoint_update_failed"
+        result["checkpoint_error"] = checkpoint_error
+    return result
+
+
+def format_result(result):
+    status = result.get("status") or result.get("gate", "")
+    if status == "GATE:START":
+        return "GATE:START marker={}".format(result.get("marker", ""))
+    if status == "MISSING":
+        return "GATE:MISSING marker={}".format(result.get("marker", ""))
+    if status == "PASS":
+        return "GATE:PASS {}".format(result.get("report", ""))
+
+    ordered = [
+        "reason",
+        "verdict",
+        "mode",
+        "artifact_dir",
+        "boundary_gate",
+        "boundary_missing",
+        "happy_path_only",
+        "boundary_validation",
+        "validator_passed",
+        "scope_fresh",
+        "openapi",
+        "report",
+        "checkpoint_error",
+        "error",
+    ]
+    parts = []
+    for key in ordered:
+        value = result.get(key)
+        if value is not None and value != "":
+            parts.append("{}={}".format(key, value))
+    return "GATE:FAIL {}".format(" ".join(parts)).rstrip()
+
+
+def build_parser():
+    parser = argparse.ArgumentParser(
+        description="Run the scoped PrizmKit feature test gate.",
+    )
+    subparsers = parser.add_subparsers(dest="command", required=True)
+
+    start = subparsers.add_parser("start", help="Create the test gate marker")
+    start.add_argument("--feature-slug", required=True)
+
+    check = subparsers.add_parser("check", help="Validate the latest scoped test report")
+    check.add_argument("--feature-slug", required=True)
+    check.add_argument("--artifact-dir", default="")
+    check.add_argument("--checkpoint-path", default="")
+    return parser
+
+
+def main(argv=None):
+    parser = build_parser()
+    args = parser.parse_args(argv)
+    if args.command == "start":
+        result = start_gate(args.feature_slug)
+    else:
+        result = check_gate(args.feature_slug, args.artifact_dir, args.checkpoint_path)
+    print(format_result(result))
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

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

@@ -30,7 +30,7 @@ Infer what needs to be done from the feature context above and follow the standa
 
 3. **Implement**: Run `/prizmkit-implement` with `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/` to execute the plan using TDD (write tests first, then implement).
 
-4. **Test**: Run the project test suite to verify all tests pass with no regressions.
+4. **Test**: Run `/prizmkit-test scope=this-change artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/` to generate and verify tests only for this feature's changed scope. Do not use bugfix/refactor artifact directories for this gate.
 
 5. **Review**: Run `/prizmkit-code-review` with `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/` to review and auto-fix changes against the spec (internal review-fix loop, max 3 rounds).
 

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

@@ -163,6 +163,20 @@ When tests fail, use convergence recovery — keep fixing while progress is bein
 **Key rule**: If failures decrease (even by 1), plateau counter resets. Do NOT block commit for unresolved failures — document and defer to next session.
 
 
+### Scoped Feature Test Gate — PrizmKit Test
+
+Run `/prizmkit-test scope=this-change artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/` after implementation and before review/commit.
+
+Before invoking the skill, create `.prizmkit/specs/{{FEATURE_SLUG}}/.prizmkit-test-started` so stale reports are ignored.
+
+Gate requirements:
+- Generate or update tests only for this feature's changed files, changed public interfaces, and acceptance criteria.
+- Do NOT use `.prizmkit/bugfix/` or `.prizmkit/refactor/` artifact directories.
+- Record unrelated historical gaps under `Out of Scope Gaps`; do not generate tests for them and do not fail this feature because of them.
+- Accept only a current-run `.prizmkit/test/*/test-report.md` whose `Scope` mode is `this-change`, whose `Artifact Dir` matches `.prizmkit/specs/{{FEATURE_SLUG}}/`, whose `Verdict` is `PASS`, whose `Boundary Completion Gate` reports `Completion gate passed: yes` with zero `Boundary-missing` and zero `Happy-path-only`, and whose `Boundary Validation` result is `passed`.
+- Only after a valid `PASS`, write the report path to `.prizmkit/specs/{{FEATURE_SLUG}}/test-report-path.txt` and append a 3-5 bullet `## PrizmKit Test Gate` summary to `context-snapshot.md`.
+- If the report verdict is `NEEDS_FIXES`, fix in-scope implementation/test issues and rerun `/prizmkit-test`. If the report is `BLOCKED`, missing, stale, or for the wrong scope/artifact dir, write `failure-log.md` and stop for recovery.
+
 {{IF_BROWSER_INTERACTION}}
 ### Phase 3.5: Browser Verification — MANDATORY
 

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

@@ -240,6 +240,20 @@ grep -q "## Implementation Log" .prizmkit/specs/{{FEATURE_SLUG}}/context-snapsho
 ```
 If GATE:MISSING — send message to Dev (re-spawn if needed): "Write the '## Implementation Log' section to context-snapshot.md before I can proceed to review. Include: files changed/created, key decisions, deviations from plan, notable discoveries."
 
+### Scoped Feature Test Gate — PrizmKit Test
+
+Run `/prizmkit-test scope=this-change artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/` after implementation and before review/commit.
+
+Before invoking the skill, create `.prizmkit/specs/{{FEATURE_SLUG}}/.prizmkit-test-started` so stale reports are ignored.
+
+Gate requirements:
+- Generate or update tests only for this feature's changed files, changed public interfaces, and acceptance criteria.
+- Do NOT use `.prizmkit/bugfix/` or `.prizmkit/refactor/` artifact directories.
+- Record unrelated historical gaps under `Out of Scope Gaps`; do not generate tests for them and do not fail this feature because of them.
+- Accept only a current-run `.prizmkit/test/*/test-report.md` whose `Scope` mode is `this-change`, whose `Artifact Dir` matches `.prizmkit/specs/{{FEATURE_SLUG}}/`, whose `Verdict` is `PASS`, whose `Boundary Completion Gate` reports `Completion gate passed: yes` with zero `Boundary-missing` and zero `Happy-path-only`, and whose `Boundary Validation` result is `passed`.
+- Only after a valid `PASS`, write the report path to `.prizmkit/specs/{{FEATURE_SLUG}}/test-report-path.txt` and append a 3-5 bullet `## PrizmKit Test Gate` summary to `context-snapshot.md`.
+- If the report verdict is `NEEDS_FIXES`, fix in-scope implementation/test issues and rerun `/prizmkit-test`. If the report is `BLOCKED`, missing, stale, or for the wrong scope/artifact dir, write `failure-log.md` and stop for recovery.
+
 ### Phase 5: Review + Test — Reviewer Subagent
 
 Spawn Reviewer subagent (Agent tool, subagent_type="prizm-dev-team-reviewer", run_in_background=false).
@@ -250,9 +264,10 @@ 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
 > 2. Read `.prizmkit/specs/{{FEATURE_SLUG}}/plan.md` for architecture decisions and completed tasks
-> 3. Run /prizmkit-code-review with artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/. The skill runs an internal review-fix loop (Reviewer → filter → Dev fix, max 3 rounds) and writes review-report.md.
-> 4. Run the full test suite using `{{TEST_CMD}}`. When running: `({{TEST_CMD}}) 2>&1 | tee /tmp/review-test-out.txt | tail -20`, then grep the file for details — do NOT re-run the suite multiple times.
-> 5. review-report.md will be written to .prizmkit/specs/{{FEATURE_SLUG}}/ by prizmkit-code-review.
+> 3. Read `.prizmkit/specs/{{FEATURE_SLUG}}/test-report-path.txt`, then read the referenced `/prizmkit-test` report. Review generated/updated tests, `In-Scope Failures`, `Baseline Failures`, `Out of Scope Gaps`, boundary coverage if present, and the report verdict.
+> 4. Run /prizmkit-code-review with artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/. The skill runs an internal review-fix loop (Reviewer → filter → Dev fix, max 3 rounds) and writes review-report.md.
+> 5. Run the full test suite using `{{TEST_CMD}}`. When running: `({{TEST_CMD}}) 2>&1 | tee /tmp/review-test-out.txt | tail -20`, then grep the file for details — do NOT re-run the suite multiple times.
+> 6. review-report.md will be written to .prizmkit/specs/{{FEATURE_SLUG}}/ by prizmkit-code-review.
 > Report: verdict (PASS/NEEDS_FIXES), number of rounds, findings fixed/rejected."
 
 Wait for Reviewer to return.

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

@@ -301,6 +301,20 @@ Wait for Dev to return. **If Dev times out before all tasks are `[x]`**:
 
 All tasks `[x]`, tests pass.
 
+### Scoped Feature Test Gate — PrizmKit Test
+
+Run `/prizmkit-test scope=this-change artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/` after implementation and before review/commit.
+
+Before invoking the skill, create `.prizmkit/specs/{{FEATURE_SLUG}}/.prizmkit-test-started` so stale reports are ignored.
+
+Gate requirements:
+- Generate or update tests only for this feature's changed files, changed public interfaces, and acceptance criteria.
+- Do NOT use `.prizmkit/bugfix/` or `.prizmkit/refactor/` artifact directories.
+- Record unrelated historical gaps under `Out of Scope Gaps`; do not generate tests for them and do not fail this feature because of them.
+- Accept only a current-run `.prizmkit/test/*/test-report.md` whose `Scope` mode is `this-change`, whose `Artifact Dir` matches `.prizmkit/specs/{{FEATURE_SLUG}}/`, whose `Verdict` is `PASS`, whose `Boundary Completion Gate` reports `Completion gate passed: yes` with zero `Boundary-missing` and zero `Happy-path-only`, and whose `Boundary Validation` result is `passed`.
+- Only after a valid `PASS`, write the report path to `.prizmkit/specs/{{FEATURE_SLUG}}/test-report-path.txt` and append a 3-5 bullet `## PrizmKit Test Gate` summary to `context-snapshot.md`.
+- If the report verdict is `NEEDS_FIXES`, fix in-scope implementation/test issues and rerun `/prizmkit-test`. If the report is `BLOCKED`, missing, stale, or for the wrong scope/artifact dir, write `failure-log.md` and stop for recovery.
+
 ### Phase 5: Review + Test — Reviewer Agent
 
 Spawn Reviewer agent (Agent tool, subagent_type="prizm-dev-team-reviewer", run_in_background=false).
@@ -311,9 +325,10 @@ 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
 > 2. Read `.prizmkit/specs/{{FEATURE_SLUG}}/plan.md` for architecture decisions and completed tasks
-> 3. Run /prizmkit-code-review with artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/. The skill runs an internal review-fix loop (Reviewer → filter → Dev fix, max 3 rounds) and writes review-report.md.
-> 4. Run the full test suite using `{{TEST_CMD}}`. When running tests: `({{TEST_CMD}}) 2>&1 | tee /tmp/review-test-out.txt | tail -20`, then grep `/tmp/review-test-out.txt` for details — do NOT re-run the suite multiple times.
-> 5. review-report.md will be written to .prizmkit/specs/{{FEATURE_SLUG}}/ by prizmkit-code-review.
+> 3. Read `.prizmkit/specs/{{FEATURE_SLUG}}/test-report-path.txt`, then read the referenced `/prizmkit-test` report. Review generated/updated tests, `In-Scope Failures`, `Baseline Failures`, `Out of Scope Gaps`, boundary coverage if present, and the report verdict.
+> 4. Run /prizmkit-code-review with artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/. The skill runs an internal review-fix loop (Reviewer → filter → Dev fix, max 3 rounds) and writes review-report.md.
+> 5. Run the full test suite using `{{TEST_CMD}}`. When running tests: `({{TEST_CMD}}) 2>&1 | tee /tmp/review-test-out.txt | tail -20`, then grep `/tmp/review-test-out.txt` for details — do NOT re-run the suite multiple times.
+> 6. review-report.md will be written to .prizmkit/specs/{{FEATURE_SLUG}}/ by prizmkit-code-review.
 > Report: verdict (PASS/NEEDS_FIXES), number of rounds, findings fixed/rejected."
 
 Wait for Reviewer to return.

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

@@ -70,13 +70,13 @@ python3 $PIPELINE_DIR/scripts/update-checkpoint.py \
   --status completed
 ```
 
-### TERMINAL STOP — S09 Completed
+### TERMINAL STOP — Commit Completed
 
 After all of the following are true, the session is **TERMINAL**:
 
 - `/prizmkit-committer` has completed
 - `git status --short` is clean (except ignored/local-only pipeline artifacts)
 - `.prizmkit/specs/{{FEATURE_SLUG}}/completion-summary.json` is written
-- the S09 / `prizmkit-committer` checkpoint is marked `completed`
+- the `prizmkit-committer` checkpoint is marked `completed`
 
 At that point, stop immediately. Do **not** process delayed teammate/reviewer findings, do **not** edit files, do **not** amend the commit, and do **not** start any new tool calls. Any findings that arrive after S09 is completed are follow-up work for a later session, not part of this feature commit.

package/bundled/dev-pipeline/templates/sections/phase-commit.md

@@ -63,13 +63,13 @@ python3 $PIPELINE_DIR/scripts/update-checkpoint.py \
   --status completed
 ```
 
-### TERMINAL STOP — S09 Completed
+### TERMINAL STOP — Commit Completed
 
 After all of the following are true, the session is **TERMINAL**:
 
 - `/prizmkit-committer` has completed
 - `git status --short` is clean (except ignored/local-only pipeline artifacts)
 - `.prizmkit/specs/{{FEATURE_SLUG}}/completion-summary.json` is written
-- the S09 / `prizmkit-committer` checkpoint is marked `completed`
+- the `prizmkit-committer` checkpoint is marked `completed`
 
 At that point, stop immediately. Do **not** process delayed teammate/reviewer findings, do **not** edit files, do **not** amend the commit, and do **not** start any new tool calls. Any findings that arrive after S09 is completed are follow-up work for a later session, not part of this feature commit.

package/bundled/dev-pipeline/templates/sections/phase-prizmkit-test.md

@@ -0,0 +1,39 @@
+### Scoped Feature Test Gate — PrizmKit Test
+
+**Goal**: Generate and verify tests for this feature's changed scope before code review without embedding the full gate implementation in this prompt.
+
+Create a start marker immediately before invoking the skill so the gate can reject stale reports from older sessions:
+
+```bash
+python3 "$PIPELINE_DIR/scripts/prizmkit-test-gate.py" start \
+  --feature-slug "{{FEATURE_SLUG}}"
+```
+
+Run `/prizmkit-test` with the feature artifact directory:
+
+```text
+/prizmkit-test scope=this-change artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/
+```
+
+Rules:
+- This gate is feature-pipeline only. Do NOT use `.prizmkit/bugfix/` or `.prizmkit/refactor/` artifact directories here.
+- Generate or update tests only for this feature's changed files, changed public interfaces, and acceptance criteria.
+- Record unrelated historical coverage gaps under `Out of Scope Gaps`; do not generate tests for them and do not fail this feature because of them.
+- If generated tests fail because implementation is wrong, fix implementation within this feature scope and rerun the affected tests.
+- If failures are baseline or unrelated to this feature, document them in the report and continue only when no in-scope failure remains unexplained.
+
+**Gate Check — Test Report**:
+After `/prizmkit-test` returns, run the gate script to locate the newest current-run report, validate scope/freshness/boundary coverage, write `test-report-path.txt`, and mark the `prizmkit-test` checkpoint completed only on `GATE:PASS`:
+
+```bash
+python3 "$PIPELINE_DIR/scripts/prizmkit-test-gate.py" check \
+  --feature-slug "{{FEATURE_SLUG}}" \
+  --artifact-dir ".prizmkit/specs/{{FEATURE_SLUG}}/" \
+  --checkpoint-path "{{CHECKPOINT_PATH}}"
+```
+
+Gate outcomes:
+- `GATE:PASS` → append the report path and a 3-5 bullet summary to `context-snapshot.md` under `## PrizmKit Test Gate`, then proceed to the next checkpoint step. The gate script already wrote `test-report-path.txt` and marked `prizmkit-test` completed.
+- `GATE:FAIL` with `NEEDS_FIXES` → read the report's `In-Scope Failures`, fix the feature implementation or generated tests within this feature scope, rerun `/prizmkit-test`, and repeat the gate check. Do not proceed to code review while the verdict is not `PASS`.
+- `GATE:FAIL` with `BLOCKED`, wrong mode, wrong artifact dir, unreadable report, stale scope, boundary failure, validator failure, or checkpoint update failure → write `.prizmkit/specs/{{FEATURE_SLUG}}/failure-log.md` with the scoped test failure and stop for recovery.
+- `GATE:MISSING` → perform one bounded status check: inspect `/prizmkit-test` output and `.prizmkit/test/` for a report directory. If no current-run report exists, write `failure-log.md` and stop for recovery.

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

@@ -1,4 +1,8 @@
-### Review + Test — Code Review
+### Review — Code Review
+
+Precondition: the `prizmkit-test` checkpoint is completed and `.prizmkit/specs/{{FEATURE_SLUG}}/test-report-path.txt` points to the scoped test report.
+
+Before invoking review, read `.prizmkit/specs/{{FEATURE_SLUG}}/test-report-path.txt`, read the referenced `/prizmkit-test` report, and confirm the summary in `context-snapshot.md` under `## PrizmKit Test Gate` matches it. The code-review skill must receive this context through `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/` and the Reviewer must assess generated/updated test quality, `In-Scope Failures`, `Baseline Failures`, `Out of Scope Gaps`, boundary coverage if present, and the scoped report verdict.
 
 Run `/prizmkit-code-review` with `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/`.
 

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

@@ -1,4 +1,8 @@
-### Review + Test — Code Review
+### Review — Code Review
+
+Precondition: the `prizmkit-test` checkpoint is completed and `.prizmkit/specs/{{FEATURE_SLUG}}/test-report-path.txt` points to the scoped test report.
+
+Before invoking review, read `.prizmkit/specs/{{FEATURE_SLUG}}/test-report-path.txt`, read the referenced `/prizmkit-test` report, and confirm the summary in `context-snapshot.md` under `## PrizmKit Test Gate` matches it. The code-review skill must receive this context through `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/` and the Reviewer must assess generated/updated test quality, `In-Scope Failures`, `Baseline Failures`, `Out of Scope Gaps`, boundary coverage if present, and the scoped report verdict.
 
 Run `/prizmkit-code-review` with `artifact_dir=.prizmkit/specs/{{FEATURE_SLUG}}/`.
 

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

@@ -24,4 +24,5 @@ def _load_hyphenated_module(module_name, filename):
 # 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")
+_load_hyphenated_module("prizmkit_test_gate", "prizmkit-test-gate.py")
 _load_hyphenated_module("update_feature_status", "update-feature-status.py")