@windyroad/itil 0.61.1 → 0.61.2

package/skills/work-problems/test/work-problems-above-appetite-remediation.bats

@@ -1,139 +0,0 @@
-#!/usr/bin/env bats
-# Doc-lint guard: work-problems SKILL.md must include the above-appetite
-# auto-apply + halt-on-exhaustion branch per ADR-042.
-#
-# Structural assertion — Permitted Exception to the source-grep ban (ADR-005 / P011).
-# These assertions are load-bearing-string checks on the skill specification
-# document. Per P081, structural tests are placeholders for behavioural tests
-# against P012's skill-testing harness; until that harness lands, these
-# assertions are the confirmation mechanism called out in ADR-042 Confirmation
-# criterion 2.
-#
-# Cross-reference:
-#   P103 (work-problems escalates resolved release decisions — defeats AFK)
-#   P104 (partial-progress paints release queue into corner)
-#   P108 (scorer remediation action-class vocabulary — deferred work)
-#   ADR-042 (auto-apply scorer remediations — open vocabulary — never release above appetite)
-#   ADR-037 (skill testing strategy — contract-assertion pattern)
-#   @jtbd JTBD-006 (Progress the Backlog While I'm Away)
-
-setup() {
-  SKILL_DIR="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)"
-  SKILL_FILE="${SKILL_DIR}/SKILL.md"
-}
-
-@test "SKILL.md exists" {
-  [ -f "$SKILL_FILE" ]
-}
-
-@test "SKILL.md cites ADR-042 (above-appetite auto-apply)" {
-  # ADR-042 Confirmation criterion 1: source review names the ADR.
-  run grep -n "ADR-042" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md contains the never-release-above-appetite invariant (Rule 1)" {
-  # The load-bearing invariant from Rule 1. "MUST NOT release above appetite"
-  # is the phrase that anchors the policy.
-  run grep -nE "MUST NOT release above appetite" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md references RISK_REMEDIATIONS parsing contract (Rule 2)" {
-  # Rule 2 parses RISK_REMEDIATIONS from the scorer. If the string is absent,
-  # the skill does not implement the parse step.
-  run grep -n "RISK_REMEDIATIONS" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md does not use a held-changeset directory as remediation" {
-  run grep -n "docs/changesets-holding/" "$SKILL_FILE"
-  [ "$status" -ne 0 ]
-}
-
-@test "SKILL.md does not offer move-to-holding as a remediation" {
-  run grep -n "move-to-holding" "$SKILL_FILE"
-  [ "$status" -ne 0 ]
-}
-
-@test "SKILL.md offers shipment-affecting remediation classes" {
-  run grep -nE "split-change|disable-or-revert|revert-commit" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md names P108 (deferred action-class vocabulary)" {
-  # Rule 2a defers revert-commit, amend-commit, feature-flag, rollback-to-tag
-  # to P108. Keeping the reference greppable makes the deferral auditable.
-  run grep -n "P108" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md includes the Verification Pending carve-out (Rule 2b)" {
-  # Rule 2b prevents auto-revert of commits attached to .verifying.md tickets.
-  run grep -niE "Verification Pending.*carve.out|Rule 2b|\.verifying\.md.*(skip|exclude|carve)" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md references the halt-on-exhaustion outcome (Rule 5)" {
-  # Rule 5 emits outcome: halted-above-appetite when the auto-apply loop
-  # exhausts without convergence.
-  run grep -n "halted-above-appetite" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md cites ADR-013 Rule 5 (policy-authorised silent proceed)" {
-  # Rule 1 is authorised by ADR-013 Rule 5. The citation should be explicit.
-  run grep -nE "ADR-013 Rule 5" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md references the scorer-gap halt signal" {
-  # Rule 5 treats exhaustion as a scorer-gap bug signal, not routine behaviour.
-  run grep -niE "scorer.gap|scorer vocabulary|bug signal" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md Non-Interactive Decision Making table covers above-appetite auto-apply" {
-  # The non-interactive defaults table row makes the behaviour discoverable to
-  # an AFK reader without forcing a full prose read.
-  run grep -niE "above appetite.*>= 5/25|pipeline risk above appetite|auto-apply scorer remediations" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md forbids AskUserQuestion shortcut for above-appetite" {
-  # The anti-shortcut stance is load-bearing for P103. Absent this, the skill
-  # reverts to the P103 bug. Allow optional "call "/"invoke " verb and optional
-  # backtick around the tool name (since the SKILL.md phrasing treats it as code).
-  run grep -niE "MUST NOT (call |invoke )?[\`]?AskUserQuestion" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md references the amend-based folding rule for ADR-032 compatibility (Rule 3)" {
-  # Auto-apply commits fold into the iteration's main commit via amend so
-  # ADR-032's one-commit-per-iteration invariant holds.
-  run grep -niE "amend|git commit --amend" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md references the audit-trail subsection (Rule 6)" {
-  # Rule 6 emits an Auto-apply trail subsection in the iteration summary. If
-  # the phrase is missing, audit trail is not wired through.
-  run grep -niE "Auto-apply trail|audit trail" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# P108: agent reads prose descriptions; no action_class column
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "SKILL.md has no action_class column reference (P108 — agent decides from prose)" {
-  # ADR-042 Rule 2a: no structured action_class column.
-  run grep -n "action_class" "$SKILL_FILE"
-  [ "$status" -ne 0 ]
-}
-
-@test "SKILL.md includes revert-commit example (P108)" {
-  # The orchestrator may choose to revert a commit based on scorer prose.
-  run grep -n "git revert" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}

package/skills/work-problems/test/work-problems-adr-013-rule-6-p352-amendment.bats

@@ -1,166 +0,0 @@
-#!/usr/bin/env bats
-# ADR-013 Rule 6 P352 amendment (2026-06-06): queue-and-continue is the
-# universal AFK default when a skill needs user input but AskUserQuestion is
-# unavailable. HALT/SKIP/AUTO-DEFAULT are deviations requiring inline-cited
-# carve-out justification.
-#
-# Structural assertion — Permitted Exception to the source-grep ban (ADR-005 /
-# P011). These assertions are load-bearing-string checks on the ADR + SKILL
-# specification prose. Per P081, structural tests are placeholders for
-# behavioural tests against P012's skill-testing harness; until the harness
-# can exercise AFK fallback shapes, prose assertions on the carve-out audit
-# are the confirmation mechanism named in the amended Rule 6 Confirmation
-# section.
-#
-# tdd-review: structural-permitted (justification: ADR Rule 6 + SKILL.md prose
-# contract assertions for an interaction-pattern contract that has no
-# behavioural skill-runtime harness yet — P012 + P081 Phase 2 bridge window.
-# Isomorphic precedent in this repo: work-problems-above-appetite-remediation.bats,
-# create-adr-substance-confirm-pattern.bats, create-adr-adr-044-contract.bats.)
-#
-# @problem P352 (AFK queue-and-continue is the universal default)
-# @adr ADR-013 (structured user interaction; Rule 6 amended 2026-06-06)
-# @adr ADR-044 (decision-delegation contract; AUTO-DEFAULT lives inside framework-resolution)
-# @adr ADR-052 (behavioural-by-default with structural bridge window)
-# @adr ADR-074 (confirm decision substance before building; authorises HALT carve-outs)
-# @jtbd JTBD-006 (Progress the Backlog While I'm Away — primary persona)
-# @jtbd JTBD-001 (Enforce Governance Without Slowing Down — queue keeps governance on during AFK)
-
-setup() {
-  REPO_ROOT="$(cd "$(dirname "$BATS_TEST_FILENAME")/../../../../.." && pwd)"
-  ADR_013="${REPO_ROOT}/docs/decisions/013-structured-user-interaction-for-governance-decisions.proposed.md"
-}
-
-# ----------------------------------------------------------------------
-# ADR-013 Rule 6 amendment prose
-# ----------------------------------------------------------------------
-
-@test "ADR-013 file exists" {
-  [ -f "$ADR_013" ]
-}
-
-@test "ADR-013 Rule 6 names queue-and-continue as the universal default (P352 amendment)" {
-  # The load-bearing prose: queue-and-continue is THE universal default.
-  run grep -nE "queue-and-continue is the universal default" "$ADR_013"
-  [ "$status" -eq 0 ]
-}
-
-@test "ADR-013 Rule 6 dates the amendment (2026-06-06)" {
-  # Date-anchoring lets future readers correlate the prose with P352 timeline.
-  run grep -nE "2026-06-06 amendment" "$ADR_013"
-  [ "$status" -eq 0 ]
-}
-
-@test "ADR-013 Rule 6 names halt-with-directive AND silent-skip as deviations" {
-  # The amendment's contract: HALT and SKIP are DEVIATIONS requiring carve-out
-  # justification — they are not the default.
-  run grep -nE "DEVIATIONS that require an explicit" "$ADR_013"
-  [ "$status" -eq 0 ]
-}
-
-@test "ADR-013 Rule 6 documents the capture-problem HALT carve-out (ADR-074 authority)" {
-  # The amendment must explicitly name the documented HALT carve-outs so
-  # readers know the SKILL surfaces that LEGITIMATELY halt and why.
-  run grep -nE "capture-problem.*derive-then-ratify HALT" "$ADR_013"
-  [ "$status" -eq 0 ]
-}
-
-@test "ADR-013 Rule 6 documents the create-adr Step 5 HALT carve-out" {
-  run grep -nE "create-adr.*Step 5 substance-confirm HALT" "$ADR_013"
-  [ "$status" -eq 0 ]
-}
-
-@test "ADR-013 Rule 6 documents the manage-problem create-gate HALT carve-out" {
-  run grep -nE "manage-problem.*create-gate HALT" "$ADR_013"
-  [ "$status" -eq 0 ]
-}
-
-@test "ADR-013 Rule 6 names AUTO-DEFAULT as framework-resolved-only (ADR-044 boundary)" {
-  # AUTO-DEFAULT is permitted ONLY when the decision is framework-resolved.
-  # Outside the framework-resolution boundary, AUTO-DEFAULT is a defect.
-  run grep -nE "AUTO-DEFAULT.*permitted ONLY when the decision is framework-resolved" "$ADR_013"
-  [ "$status" -eq 0 ]
-}
-
-@test "ADR-013 Rule 6 cites ADR-044 (decision-delegation framework-resolution boundary)" {
-  run grep -nE "ADR-044" "$ADR_013"
-  [ "$status" -eq 0 ]
-}
-
-@test "ADR-013 Rule 6 cites ADR-074 (substance-confirm authority for HALT carve-outs)" {
-  run grep -nE "ADR-074" "$ADR_013"
-  [ "$status" -eq 0 ]
-}
-
-@test "ADR-013 Rule 6 cites JTBD-006 (Progress the Backlog While I'm Away)" {
-  run grep -nE "JTBD-006" "$ADR_013"
-  [ "$status" -eq 0 ]
-}
-
-@test "ADR-013 Rule 6 cites P352 as the originating ticket" {
-  run grep -nE "\bP352\b" "$ADR_013"
-  [ "$status" -eq 0 ]
-}
-
-@test "ADR-013 Rule 6 records the shared-helper extraction as a follow-on (deferred)" {
-  # The ratified design explicitly deferred the shared-helper extraction to
-  # follow-on. The prose must record the deferral so future readers (and
-  # future iter agents) know the interim contract.
-  run grep -nE "Shared-helper extraction deferred" "$ADR_013"
-  [ "$status" -eq 0 ]
-}
-
-# ----------------------------------------------------------------------
-# Per-SKILL carve-out audit annotations
-# ----------------------------------------------------------------------
-
-@test "capture-problem SKILL.md carries the P352 carve-out audit (P401-corrected: conforms to queue-and-continue; ADR-074 preserved via downstream gating)" {
-  SKILL="${REPO_ROOT}/packages/itil/skills/capture-problem/SKILL.md"
-  [ -f "$SKILL" ]
-  run grep -nE "ADR-013 Rule 6 carve-out audit \(P352" "$SKILL"
-  [ "$status" -eq 0 ]
-  # Post-P401 (2026-06-29/2026-07-02) the AFK low-confidence path no longer
-  # HALTs — it CONFORMS to the queue-and-continue default: capture the
-  # ticket with the unconfirmed-anchoring sentinel + queue the elicitation.
-  run grep -niE "conform.*queue-and-continue|unconfirmed — elicitation queued" "$SKILL"
-  [ "$status" -eq 0 ]
-  # ADR-074 is still named as the honoured constraint (preserved by
-  # downstream oversight gating, not by a no-ticket halt).
-  run grep -nE "ADR-074" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-@test "create-adr SKILL.md carries the P352 carve-out audit (Step 1 AUTO-DEFAULT + Step 5 HALT)" {
-  SKILL="${REPO_ROOT}/packages/architect/skills/create-adr/SKILL.md"
-  [ -f "$SKILL" ]
-  run grep -nE "ADR-013 Rule 6 carve-out audit \(P352" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-@test "manage-problem SKILL.md carries the P352 carve-out audit (Step 4b AUTO-DEFAULT)" {
-  SKILL="${REPO_ROOT}/packages/itil/skills/manage-problem/SKILL.md"
-  [ -f "$SKILL" ]
-  run grep -nE "ADR-013 Rule 6 carve-out audit \(P352" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-@test "review-problems SKILL.md cites the P352 amendment at the Step 4.5 AFK branch" {
-  SKILL="${REPO_ROOT}/packages/itil/skills/review-problems/SKILL.md"
-  [ -f "$SKILL" ]
-  run grep -nE "ADR-013 Rule 6 universal default \(P352" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-@test "scaffold-intake SKILL.md cites the P352 amendment as canonical queue-and-continue" {
-  SKILL="${REPO_ROOT}/packages/itil/skills/scaffold-intake/SKILL.md"
-  [ -f "$SKILL" ]
-  run grep -nE "ADR-013 Rule 6 universal default \(P352" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-@test "run-retro SKILL.md cites the P352 amendment at the Step 1.5 AFK branch" {
-  SKILL="${REPO_ROOT}/packages/retrospective/skills/run-retro/SKILL.md"
-  [ -f "$SKILL" ]
-  run grep -nE "ADR-013 Rule 6 universal default \(P352" "$SKILL"
-  [ "$status" -eq 0 ]
-}

package/skills/work-problems/test/work-problems-auto-migrate-step.bats

@@ -1,57 +0,0 @@
-#!/usr/bin/env bats
-
-# P170 / RFC-002 / ADR-031 Open-Execution Q1 resolution: work-problems
-# SKILL.md wires the shared migration routine at Step 0a (after Step 0
-# fetch/divergence preflight, before Step 1 backlog scan). Closes the
-# Step 1 false-zero defect — flat-layout adopters without auto-migrate
-# at Step 0a would enumerate zero matches at Step 1 and stop-condition
-# would fire incorrectly. Doc-lint structural test — behavioural
-# assertions live at packages/shared/test/sync-migrate-problems-layout.bats
-# (T7) and the end-to-end behavioural fixture
-# packages/itil/skills/work-problems/test/work-problems-auto-migrate.bats (T10).
-
-setup() {
-  REPO_ROOT="$(cd "$(dirname "$BATS_TEST_FILENAME")/../../../../.." && pwd)"
-  SKILL_MD="$REPO_ROOT/packages/itil/skills/work-problems/SKILL.md"
-}
-
-@test "work-problems: SKILL.md declares Step 0a auto-migrate (T9 wiring point)" {
-  run grep -E '^### Step 0a:|^### 0a\.|Step 0a:' "$SKILL_MD"
-  [ "$status" -eq 0 ]
-}
-
-@test "work-problems: SKILL.md Step 0a cites P170 / RFC-002 / ADR-031" {
-  run grep -F 'P170' "$SKILL_MD"
-  [ "$status" -eq 0 ]
-  run grep -F 'ADR-031' "$SKILL_MD"
-  [ "$status" -eq 0 ]
-}
-
-@test "work-problems: SKILL.md Step 0a sources packages/itil/lib/migrate-problems-layout.sh" {
-  run grep -F 'packages/itil/lib/migrate-problems-layout.sh' "$SKILL_MD"
-  [ "$status" -eq 0 ]
-}
-
-@test "work-problems: SKILL.md Step 0a calls migrate_problems_to_per_state_layout entrypoint" {
-  run grep -F 'migrate_problems_to_per_state_layout' "$SKILL_MD"
-  [ "$status" -eq 0 ]
-}
-
-@test "work-problems: SKILL.md Step 0a fires AFTER Step 0 fetch/divergence and BEFORE Step 1 backlog scan" {
-  local step_0_line step_0a_line step_1_line
-  step_0_line=$(grep -nE '^### Step 0:' "$SKILL_MD" | head -1 | cut -d: -f1)
-  step_0a_line=$(grep -nE '^### Step 0a:' "$SKILL_MD" | head -1 | cut -d: -f1)
-  step_1_line=$(grep -nE '^### Step 1:' "$SKILL_MD" | head -1 | cut -d: -f1)
-  [ -n "$step_0_line" ]
-  [ -n "$step_0a_line" ]
-  [ -n "$step_1_line" ]
-  [ "$step_0_line" -lt "$step_0a_line" ]
-  [ "$step_0a_line" -lt "$step_1_line" ]
-}
-
-@test "work-problems: SKILL.md Step 0a addresses the Step 1 false-zero defect (ADR-031 Backward Compatibility)" {
-  # Architect explicitly noted Step 1 enumeration would mis-report
-  # "nothing to do" on flat-layout adopters without Step 0a wiring.
-  run grep -E 'false.zero|Step 1 enumerat|flat-layout adopter' "$SKILL_MD"
-  [ "$status" -eq 0 ]
-}

package/skills/work-problems/test/work-problems-cost-logging.bats

@@ -1,109 +0,0 @@
-#!/usr/bin/env bats
-# Doc-lint guard: work-problems SKILL.md must extract cost + usage metadata
-# from each iteration's `claude -p --output-format json` response, surface it
-# in the per-iteration Step 6 progress line, and aggregate it in the ALL_DONE
-# Output Format as a dedicated "Session Cost" section.
-#
-# Rationale: the subprocess-boundary dispatch lands per-iteration cost in the
-# JSON response alongside `.result`. Without an explicit extraction contract,
-# that data is invisible to the user even though it's already emitted. Cost
-# logging lets the user calibrate AFK loop sizing on return (e.g. "max out
-# the token usage" direction 2026-04-21 needs a feedback loop).
-#
-# Structural assertion — Permitted Exception under ADR-005 + ADR-037 (SKILL.md
-# is the contract document). A behavioural harness that exercises the `jq`
-# extraction against a fixture JSON is a potential follow-up; out of scope
-# for this doc-lint pass.
-#
-# @problem P084
-# @jtbd JTBD-006
-#
-# Cross-reference:
-#   P084 (iteration worker has no Agent tool) — parent ticket; cost logging
-#     is an additive observability overlay on P084's shipped subprocess
-#     dispatch.
-#   ADR-032 (governance skill invocation patterns) — subprocess-boundary
-#     sub-pattern; `--output-format json` parse shape is already pinned.
-#   ADR-026 (agent output grounding) — Session Cost section cites its source
-#     so downstream audits can distinguish measured-actual from estimated.
-#   ADR-037 (skill testing strategy) — contract-assertion pattern.
-#   JTBD-006 (Progress the Backlog While I'm Away) — "clear summary when I
-#     return" documented outcome includes cost/token traceability.
-
-setup() {
-  SKILL_DIR="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)"
-  SKILL_FILE="${SKILL_DIR}/SKILL.md"
-}
-
-@test "SKILL.md Step 5 extracts .total_cost_usd from iteration JSON response" {
-  # Cost per iteration lives in the same JSON blob as .result; parsing it
-  # costs nothing more than a jq call the orchestrator already needs for
-  # ITERATION_SUMMARY.
-  run grep -nE 'total_cost_usd' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md Step 5 extracts usage token fields from iteration JSON response" {
-  # input_tokens / output_tokens / cache_creation_input_tokens /
-  # cache_read_input_tokens are the four usage fields that give a full
-  # accounting. Cache-read is the key signal for reuse across subprocess
-  # invocations in the same Bash session.
-  run grep -nE 'input_tokens|output_tokens|cache_creation_input_tokens|cache_read_input_tokens' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md Step 5 names jq (or equivalent) as the extraction mechanism" {
-  # jq is already implicit in `--output-format json` consumption; naming it
-  # in the SKILL.md prevents bespoke sed/awk reimplementations.
-  run grep -nE '\\bjq\\b|JSON parser|JSON extraction' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md Step 5 scopes the extraction to named fields only (PII guard)" {
-  # Architect advisory 2026-04-21: the JSON response also carries session_id,
-  # model, stop_reason, etc. that should NOT be surfaced in user-visible
-  # output. The extraction list must be explicit so future contributors
-  # don't unconsciously broaden it.
-  run grep -niE 'extract only|only the fields|do not (surface|log|emit)|scoped to (the )?named fields|explicit field list' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md Step 6 per-iteration progress line includes cost marker" {
-  # Example progress line in Step 6 should show the (cost, duration, tokens)
-  # suffix so contributors see the target format.
-  run grep -nE '\$[0-9]+\.[0-9]+.{0,40}(tokens|iteration|s,)' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md Output Format includes a Session Cost section" {
-  # ALL_DONE summary aggregates per-iteration cost across the run. The
-  # section renders in every ALL_DONE — interactive OR AFK — because it's
-  # output-side, not a decision branch.
-  run grep -nE '^### Session Cost|## Session Cost|Session Cost.{0,40}Total' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md Output Format Session Cost table includes cache-read reuse signal" {
-  # Cache-read is the signal for "warm-cache savings across subprocess
-  # invocations in the same Bash session" — empirically observed 65-147K
-  # cache-read tokens on probes 2-4 during the P084 probe sequence. Making
-  # this visible to the user helps them reason about AFK loop cost dynamics.
-  run grep -niE 'cache.?read|cache reuse|reuse signal|cache hit' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md Output Format Session Cost section cites its data source (ADR-026)" {
-  # Architect advisory: the Session Cost numbers are measured-actual (from
-  # each iteration's claude -p JSON output), not estimates. Name the source
-  # so audit / downstream-tooling can trust the numbers.
-  run grep -niE 'extracted from.{0,80}(claude -p|--output-format json|iteration)|source:.{0,80}claude -p|measured.{0,40}(iteration|subprocess)' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md Session Cost section renders in both interactive and AFK modes" {
-  # JTBD-006 Rule 6 check: Session Cost is pure output, no AskUserQuestion,
-  # no policy-authorised action. Must render identically in both modes so
-  # AFK users see the same summary on return.
-  run grep -niE 'Session Cost.{0,160}(regardless|both|interactive.{0,40}AFK|AFK.{0,40}interactive)|output-side|no decision branch' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}

package/skills/work-problems/test/work-problems-deviation-candidate-shape.bats

@@ -1,121 +0,0 @@
-#!/usr/bin/env bats
-#
-# packages/itil/skills/work-problems/test/work-problems-deviation-candidate-shape.bats
-#
-# Behavioural tests for the deviation-candidate sub-pattern in
-# ITERATION_SUMMARY.outstanding_questions (P135 Phase 3 / R7 / ADR-044).
-#
-# Per ADR-044's anti-BUFD-for-framework-evolution clause: existing
-# decisions are point-in-time; as reality changes, existing decisions
-# may become wrong. The agent MUST surface deviation candidates with
-# evidence (existing-decision citation + contradicting-evidence
-# citation per ADR-026 + proposed shape) and queue them for user
-# approval. Never auto-deviate; never blindly follow against evidence.
-#
-# This bats fixture covers the deviation-candidate schema surface in
-# the ITERATION_SUMMARY contract + Step 2.5 5-option AskUserQuestion
-# loop-end emit + jsonl persistence shape across iter subprocess
-# boundary + the positive regression assertion (not-queueing-when-
-# evidence-present is a regression).
-#
-# tdd-review: structural-permitted (justification: skill behavioural
-# harness pending P012 + P081 Phase 2; SKILL.md contract assertions
-# bridge until then; expected to migrate to behavioural form once the
-# harness exists)
-#
-# @problem P135 Phase 3 R7
-# @adr ADR-044 (Decision-Delegation Contract — deviation-approval surface)
-# @adr ADR-026 (cost-source grounding for evidence citations)
-# @adr ADR-032 (pending-questions artefact precedent for jsonl)
-# @adr ADR-005 / ADR-037 (testing strategy — bridge during harness build)
-# @jtbd JTBD-006 (AFK loop empirical-discovery surface)
-
-SKILL_FILE="${BATS_TEST_DIRNAME}/../SKILL.md"
-
-setup() {
-  [ -f "$SKILL_FILE" ]
-}
-
-# ── Deviation-candidate schema documented in ITERATION_SUMMARY contract ─────
-
-@test "SKILL.md ITERATION_SUMMARY.outstanding_questions schema documents deviation-candidate entry shape" {
-  run grep -F "deviation-approval" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  run grep -F "Deviation-candidate entry" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "deviation-candidate schema requires existing_decision citation field" {
-  run grep -F "existing_decision:" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "deviation-candidate schema requires contradicting_evidence citation per ADR-026 grounding" {
-  run grep -F "contradicting_evidence:" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  run grep -F "ADR-026" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "deviation-candidate schema requires proposed_shape ∈ {amend, supersede, one-time}" {
-  run grep -F "proposed_shape:" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  run grep -F '"amend" | "supersede" | "one-time"' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ── No-auto-deviate contract ────────────────────────────────────────────────
-
-@test "SKILL.md asserts agent does NOT auto-deviate when existing decision appears no-longer-right" {
-  run grep -F "does **NOT auto-deviate**" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md asserts agent never blindly follows against evidence" {
-  run grep -F "never blindly follows against evidence" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "Phase 3 contract: not-queueing-when-strong-contradicting-evidence-exists is a regression" {
-  run grep -F "Not-queueing-when-strong-contradicting-evidence-exists is a regression" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ── Loop-end 5-option AskUserQuestion emit ─────────────────────────────────
-
-@test "Step 2.5 deviation-candidate loop-end emit presents the 5-option AskUserQuestion" {
-  run grep -F "Approve + amend ADR" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  run grep -F "Approve + supersede ADR" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  run grep -F "Approve + one-time exception" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  run grep -F "Reject (existing decision stands)" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  run grep -F "Defer (need more evidence)" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "Step 2.5 ranking puts deviation-approval at highest precedence" {
-  run grep -F "deviation-approval (highest)" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ── Jsonl persistence across iter subprocess boundary ───────────────────────
-
-@test "SKILL.md persists outstanding_questions to .afk-run-state/outstanding-questions.jsonl" {
-  run grep -F ".afk-run-state/outstanding-questions.jsonl" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "SKILL.md cites ADR-032 pending-questions artefact precedent for the jsonl shape" {
-  run grep -F "ADR-032 pending-questions artefact precedent" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ── Anti-BUFD-for-framework-evolution clause cross-reference ────────────────
-
-@test "SKILL.md cites ADR-044's anti-BUFD-for-framework-evolution as the rationale" {
-  run grep -F "anti-BUFD-for-framework-evolution" "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}

package/skills/work-problems/test/work-problems-first-run-intake-prompt.bats

@@ -1,36 +0,0 @@
-#!/usr/bin/env bats
-
-# P065 / ADR-036 Confirmation line 199: work-problems SKILL.md must wire
-# the first-run intake-scaffold pointer + AFK fail-safe + marker contract.
-#
-# Doc-lint structural test (Permitted Exception per ADR-005). Sister bats
-# to manage-problem-first-run-intake-prompt.bats.
-
-setup() {
-  REPO_ROOT="$(cd "$(dirname "$BATS_TEST_FILENAME")/../../../../.." && pwd)"
-  SKILL_MD="$REPO_ROOT/packages/itil/skills/work-problems/SKILL.md"
-}
-
-@test "work-problems: SKILL.md cites ADR-036 (first-run-prompt contract)" {
-  run grep -F 'ADR-036' "$SKILL_MD"
-  [ "$status" -eq 0 ]
-}
-
-@test "work-problems: SKILL.md cross-references the scaffold-intake skill" {
-  run grep -F 'wr-itil:scaffold-intake' "$SKILL_MD"
-  [ "$status" -eq 0 ]
-}
-
-@test "work-problems: SKILL.md documents the AFK fail-safe (no auto-scaffold; iteration-report pending-note)" {
-  # AFK orchestrator branch must NOT auto-scaffold; instead the iteration
-  # appends a one-line "pending intake scaffold" note to its summary.
-  # The SKILL.md preamble pointer documents this so AFK consumers see
-  # the divergence at glance.
-  run grep -iE 'pending.intake.scaffold|pending intake scaffold|silent note' "$SKILL_MD"
-  [ "$status" -eq 0 ]
-}
-
-@test "work-problems: SKILL.md cites the decline marker path (ADR-009 + ADR-036)" {
-  run grep -F '.claude/.intake-scaffold-declined' "$SKILL_MD"
-  [ "$status" -eq 0 ]
-}