feat: adds stage aware schema changes and module changes

.github/workflows/ci.yml

@@ -0,0 +1,33 @@
+name: CI
+on:
+  push:
+    branches:
+      - "main"
+  pull_request:
+    branches:
+      - "main"
+
+permissions: {}
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+      - name: Setup CUE
+        uses: cue-lang/setup-cue@a93fa358375740cd8b0078f76355512b9208acb1 # v1.0.1
+        with:
+          version: "v0.17.0"
+      - name: Install Task
+        uses: go-task/setup-task@a00fbb05ce67b35648be3c78cbc9fd85354c757e # v2.2.0
+        with:
+          version: 3.x
+      - name: Run vet
+        run: task vet-examples
+      - name: Run test
+        run: task test

.github/workflows/publish-cue.yml

@@ -20,11 +20,6 @@ jobs:
         uses: cue-lang/setup-cue@a93fa358375740cd8b0078f76355512b9208acb1 # v1.0.1
         with:
           version: "v0.17.0"
-      - name: Validate examples
-        run: |
-          for f in examples/*.yaml; do
-            cue vet prd.cue "$f" -d '#PRDDocument'
-          done
       - name: Login to CUE Central Registry
         uses: cue-labs/registry-login-action@66d40052b0206031343e17173425fa10508968d0 # v1.0.3
       - name: Publish module

.gitignore

@@ -11,5 +11,18 @@ node_modules/
 .claude/
 .superpowers/
 
+# lola-eval harness: project-local venv + generated run artifacts
+.venv/
+.lola-eval/out/
+.lola-eval/runs.db
+.lola-eval/results/
+.lola-eval/*.xml
+# Provisioned into starters by provision.sh; regenerated, never committed
+.lola-eval/tests/*/starter-clean/
+.lola-eval/tests/*/starter/.gitconfig
+.lola-eval/tests/*/starter/.opencode/
+
 # Working artifacts (never committed)
 docs/superpowers/
+# Org-specific tracker scope for discovery (never committed; example is tracked)
+/discovery-tracker.yaml

.lola-eval/baseline.json

@@ -0,0 +1,11 @@
+{
+  "_schema_version": 2,
+  "claude-code/claude-sonnet-4-6/case-001-unknown-executor/project/none": {
+    "composite": 0.925,
+    "rubric_pass_threshold": 0.6
+  },
+  "claude-code/claude-sonnet-4-6/case-002-discovery-seeds-prd/project/none": {
+    "composite": 0.99,
+    "rubric_pass_threshold": 0.6
+  }
+}

.lola-eval/config.yaml

@@ -0,0 +1,39 @@
+# .lola-eval/config.yaml — Mode 1 (in-repo) spike scaffold.
+#
+# The project provisions its own pack (see provision.sh) and the harness
+# measures the agent's behaviour against that environment. Trimmed to a
+# single test cell for the initial spike; widen the matrix once the
+# harness has proven itself here.
+
+# Cases live in `.lola-eval/tests/`, not the harness default `test_sets/`.
+tests_dir: tests
+
+# Pinned to a concrete model id so composite scores stay reproducible.
+targets:
+  - cli: claude-code
+    models:
+      - claude-sonnet-4-6
+
+# Bare-model "none" pass doubles run cost; off until we want a lift study.
+calculate_baseline: false
+
+threshold:
+  mode: absolute
+  tolerance: 0.15
+  timeout_is_failure: true
+
+concurrency: 4
+
+timeouts:
+  runner_seconds: 14400   # 4h; don't let the harness kill slow cells
+  agent_seconds: 1800     # 30m per agent (matches task.yaml timeout_seconds)
+
+judges:
+  - {cli: claude-code, model: claude-sonnet-4-6}  # single judge keeps drift comparable
+
+aggregation: mean
+
+ci:
+  junit_xml: true
+  github_summary: true
+  html_report: true

.lola-eval/provision.sh

@@ -0,0 +1,129 @@
+#!/usr/bin/env bash
+# provision.sh — copy the current module/ into each starter repo so the
+# agent under test runs /prd-review with THIS commit's version of the
+# intake-kit module.
+#
+# Usage: provision.sh [module_dir]
+#   module_dir defaults to ../module (relative to this script).
+#
+# For each starter/ under .lola-eval/tests/:
+#   1. Remove any prior .lola/ and CLI integration dirs inside the starter
+#   2. Copy module/ into starter/.lola/modules/intake-kit/module/
+#   3. Write starter/.lola/modules/intake-kit/.lola/source.yml
+#   4. Copy top-level AGENTS.md, README.md, LICENSE into the module root
+#   5. Copy CLI integration files directly (.claude/, .opencode/) instead
+#      of calling `lola install` (too slow for batch use)
+#   6. Write a clean .gitconfig for eval isolation
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+MODULE_DIR="${1:-$(cd "$SCRIPT_DIR/../module" && pwd)}"
+TESTS_DIR="$SCRIPT_DIR/tests"
+PROJECT_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+
+if [[ ! -d "$MODULE_DIR" ]]; then
+  echo "provision.sh: module dir not found: $MODULE_DIR" >&2
+  exit 1
+fi
+
+if [[ ! -d "$TESTS_DIR" ]]; then
+  echo "provision.sh: tests dir not found: $TESTS_DIR" >&2
+  exit 1
+fi
+
+provisioned=0
+
+for starter in "$TESTS_DIR"/*/starter; do
+  [[ -d "$starter" ]] || continue
+  case_name="$(basename "$(dirname "$starter")")"
+
+  # Clean prior provisioning (module files + CLI integration dirs)
+  rm -rf "$starter/.lola" "$starter/.claude" "$starter/.opencode"
+
+  # Create lola module structure
+  mod_dest="$starter/.lola/modules/intake-kit"
+  mkdir -p "$mod_dest/module"
+  mkdir -p "$mod_dest/.lola"
+
+  # Copy the module contents (exclude .git to avoid embedded repo warnings)
+  cp -a "$MODULE_DIR/." "$mod_dest/module/"
+  find "$mod_dest" -name .git -type d -exec rm -rf {} + 2>/dev/null || true
+
+  # Copy top-level files that lola expects at the module root
+  for f in AGENTS.md README.md LICENSE CHANGELOG.md; do
+    if [[ -f "$PROJECT_ROOT/$f" ]]; then
+      cp "$PROJECT_ROOT/$f" "$mod_dest/$f"
+    fi
+  done
+
+  # Write lola source metadata
+  cat > "$mod_dest/.lola/source.yml" <<'YAML'
+source: local://provision
+type: local
+YAML
+
+  # Install CLI integration files directly by copying from module/. This
+  # replaces `lola install` (15-30s per invocation). The output is
+  # deterministic: agents/, commands/, skills/, references/ are straight
+  # copies of the module source files.
+  for target_dir in .claude .opencode; do
+    mkdir -p "$starter/$target_dir/agents"
+
+    if [[ -d "$MODULE_DIR/agents" ]]; then
+      cp "$MODULE_DIR/agents/"*.md "$starter/$target_dir/agents/" 2>/dev/null || true
+    fi
+
+    if [[ -d "$MODULE_DIR/commands" ]]; then
+      mkdir -p "$starter/$target_dir/commands"
+      cp "$MODULE_DIR/commands/"*.md "$starter/$target_dir/commands/" 2>/dev/null || true
+    fi
+
+    # Skills copy is recursive — carries the nested references/ under each skill.
+    if [[ -d "$MODULE_DIR/skills" ]]; then
+      cp -a "$MODULE_DIR/skills/." "$starter/$target_dir/skills/"
+    fi
+
+    if [[ -d "$MODULE_DIR/references" ]]; then
+      cp -a "$MODULE_DIR/references/." "$starter/$target_dir/references/"
+    fi
+  done
+
+  # Write clean git config for eval isolation
+  cat > "$starter/.gitconfig" <<'GIT'
+[user]
+    name = lola-eval
+    email = eval@localhost
+[commit]
+    gpgsign = false
+[init]
+    defaultBranch = main
+GIT
+
+  # Create starter-clean/ — same source, no module artifacts. Used by
+  # pack_id=none baseline runs for genuine bare-model comparison.
+  clean="$TESTS_DIR/$case_name/starter-clean"
+  rm -rf "$clean"
+  cp -a "$starter" "$clean"
+  rm -rf "$clean/.lola" "$clean/.claude" "$clean/.opencode"
+  for f in AGENTS.md CLAUDE.md; do
+    if [[ -f "$clean/$f" ]]; then
+      sed -i '/<!-- lola:module:.*:start -->/,/<!-- lola:module:.*:end -->/d' "$clean/$f"
+      sed -i '/<!-- lola:skills:start -->/,/<!-- lola:skills:end -->/d' "$clean/$f"
+      sed -i '/<!-- lola:instructions:start -->/d; /<!-- lola:instructions:end -->/d' "$clean/$f"
+      sed -i '/^## Lola Skills$/,/^<!-- lola:skills:start -->/d' "$clean/$f" 2>/dev/null || true
+      if [[ ! -s "$clean/$f" ]] || ! grep -q '[^[:space:]]' "$clean/$f" 2>/dev/null; then
+        rm -f "$clean/$f"
+      fi
+    fi
+  done
+
+  provisioned=$((provisioned + 1))
+  echo "provision.sh: provisioned $case_name (+ starter-clean)"
+done
+
+if [[ $provisioned -eq 0 ]]; then
+  echo "provision.sh: no starter dirs found under $TESTS_DIR" >&2
+  exit 1
+fi
+
+echo "provision.sh: $provisioned case(s) provisioned"

.lola-eval/tests/case-001-unknown-executor/prompt.md

@@ -0,0 +1,11 @@
+Review this PRD family using the intake-kit prd-review skill.
+
+The initiative has a parent PRD (`parent.yaml`) and one phase PRD
+(`phase1.yaml`). The `prd-review` skill and its agents are pre-installed
+in this project's `.lola/` directory. Run the review with the local
+schema as fallback:
+
+    /prd-review --schema prd.cue parent.yaml phase1.yaml
+
+Report all findings from the review, including their severity and the
+specific location (file and id) each finding refers to.

.lola-eval/tests/case-001-unknown-executor/rubric.md

@@ -0,0 +1,83 @@
+---
+rubric_version: "1"
+pass_threshold: 0.6
+weights:
+  detection: 0.5
+  evidence: 0.25
+  false_positives: 0.15
+  no_flapping: 0.10
+---
+
+# Rubric: case-001-unknown-executor
+
+The agent was asked to run `/prd-review` on a two-file PRD family
+(`parent.yaml` + `phase1.yaml`) that is schema-valid but contains one
+seeded cross-file defect:
+
+- The phase journey "Create a short link" names
+  `executor: ghost-admin`, but the parent's `job-executors` list
+  declares only `end-user`. This is the **UNKNOWN_EXECUTOR** condition —
+  a journey referencing an executor id that no parent job-executor
+  defines. It is a BLOCKER and is only catchable by the Guard agent's
+  cross-file check, since each file passes `cue vet` in isolation.
+
+Score each component in [0.0, 1.0].
+
+## detection (weight 0.5)
+
+Did the review identify the unknown executor `ghost-admin` (the journey
+referencing an executor absent from the parent's job-executors list)?
+
+- 1.0 — the review explicitly flags `ghost-admin` as an executor not
+  declared in the parent (UNKNOWN_EXECUTOR or an equivalent description),
+  at BLOCKER severity.
+- 0.5 — the review notes an executor/journey problem but is vague about
+  which executor is undefined or does not treat it as blocking.
+- 0.0 — the defect is not reported.
+
+## evidence (weight 0.25)
+
+Does the finding cite the specific location — the phase file's journey and
+the executor id `ghost-admin`, and ideally that the parent declares only
+`end-user`?
+
+- 1.0 — names `ghost-admin`, the journey it appears in, and contrasts it
+  with the parent's declared executor(s).
+- 0.5 — names the executor OR the journey but not both, or is approximate.
+- 0.0 — no specific location cited.
+
+## false_positives (weight 0.15)
+
+Did the review avoid inventing findings that do not exist? The only real
+defect is the unknown executor; the rest of the family is well-formed
+(the FR is implemented by a journey step, satisfies a real desired
+outcome, and the phase is Draft so acceptance criteria are optional).
+
+- 1.0 — zero fabricated findings.
+- 0.5 — one fabricated finding.
+- 0.0 — two or more fabricated findings.
+
+## no_flapping (weight 0.10)
+
+Did the agent load its instruction files (SKILL.md, phase files, agent
+definitions) cleanly?
+
+- 1.0 — clean load, no searching or retrying.
+- 0.5 — minor searching behavior.
+- 0.0 — extensive searching, multiple retries, or errors.
+
+## output
+
+Return strict JSON:
+
+```
+{
+  "components": {
+    "detection": "<float>",
+    "evidence": "<float>",
+    "false_positives": "<float>",
+    "no_flapping": "<float>"
+  },
+  "explanation": "<one-paragraph rationale>"
+}
+```

.lola-eval/tests/case-001-unknown-executor/starter/parent.yaml

@@ -0,0 +1,28 @@
+header:
+  schema-version: "0.1.0"
+  version: "0.1.0"
+  last-updated: "2026-01-01"
+
+slug: link-shortener
+title: "Link Shortener"
+description: >-
+  Help users turn a long URL into a short, shareable link.
+
+stakeholders:
+  - role: "Product Owner"
+    handle: "@owner"
+  - role: "Requestor"
+    handle: "@requestor"
+    approver: true
+  - role: "Stakeholder Representative"
+    handle: "@rep"
+
+job-executors:
+  - id: end-user
+    label: "End User"
+    core-job: "turn a long URL into a short link I can share and reuse"
+
+desired-outcomes:
+  - id: DO-LS-001
+    statement: "minimize the time it takes to create a short link so sharing isn't interrupted"
+    executor-id: end-user