@windyroad/risk-scorer 0.17.2 → 0.17.3

package/skills/update-policy/SKILL.md

@@ -1,7 +1,11 @@
+<!-- Generated from packages/risk-scorer/skills/*/SKILL.md by packages/risk-scorer/scripts/sync-codex-skills.mjs during npm pack. Do not edit packaged output directly. -->
+
+> Codex runtime note: use `request_user_input` where this skill needs structured user input. If a step refers to Claude-style agent dispatch or `subagent_type`, invoke the matching installed Codex agent when available; in `codex exec` or any runtime without custom-agent dispatch, perform the same review inline from the plugin's sibling `agents/*.md` instructions and preserve the structured verdict blocks.
+
 ---
 name: wr-risk-scorer:update-policy
 description: Create or update the project's RISK-POLICY.md per ISO 31000 and the risk-scorer agent. Examines the project to derive business-specific impact levels.
-allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion, Agent
+allowed-tools: Read, Write, Edit, Bash, Glob, Grep, request_user_input, Agent
 ---
 
 # Risk Policy Generator
@@ -26,7 +30,7 @@ The risk-scorer agent, problem management skill, and any other process that need
 
 ### 1. Read the risk-scorer agent contract
 
-Read `.claude/agents/risk-scorer-pipeline.md` to understand what the scorer expects from `RISK-POLICY.md`. Extract:
+Read `agents/pipeline.md` to understand what the scorer expects from `RISK-POLICY.md`. Extract:
 
 - What fields the agent reads from the policy (look for "Read `RISK-POLICY.md`" in "Your Role")
 - The impact level labels used in the agent's risk matrix (look for the "Product Reference Table")
@@ -124,9 +128,9 @@ The risk matrix is used by both the **risk-scorer agent** (pipeline risk assessm
 
 ### 6. Confirm with the user
 
-You MUST use the AskUserQuestion tool (not plain text output) to collect user confirmation. Do not proceed to step 6a or step 7 until you have received answers via AskUserQuestion.
+You MUST use the request_user_input tool (not plain text output) to collect user confirmation. Do not proceed to step 6a or step 7 until you have received answers via request_user_input.
 
-Call AskUserQuestion with a single message that presents:
+Call request_user_input with a single message that presents:
 
 1. The drafted impact levels (as a table) and asks whether they accurately reflect what matters most
 2. The risk appetite threshold -- present the label bands from the agent contract (step 1) and recommend a threshold based on project maturity. Ask the user to confirm or adjust. A prototype with no real users may tolerate higher risk than a production system with paying users or compliance requirements
@@ -134,7 +138,7 @@ Call AskUserQuestion with a single message that presents:
 
 ### 6a. Tight-appetite warning when threshold < 5 (ADR-086)
 
-If the user picked an appetite threshold below 5 in step 6, fire a second `AskUserQuestion` confirm-with-warning before proceeding. The Low band's ceiling under ADR-086 is 5; an appetite below 5 means a class of risks (those with Impact=5/Severe and no impact-reducing control available) can never be within appetite — the policy is mathematically infeasible for that class. The user can still set the tighter threshold (some domains genuinely want to prohibit severe-impact activities), but the consequence must be a conscious choice, not a quiet trap.
+If the user picked an appetite threshold below 5 in step 6, fire a second `request_user_input` confirm-with-warning before proceeding. The Low band's ceiling under ADR-086 is 5; an appetite below 5 means a class of risks (those with Impact=5/Severe and no impact-reducing control available) can never be within appetite — the policy is mathematically infeasible for that class. The user can still set the tighter threshold (some domains genuinely want to prohibit severe-impact activities), but the consequence must be a conscious choice, not a quiet trap.
 
 **Build the warning's example list** (cite concrete activity-classes the user is about to prohibit):
 
@@ -152,7 +156,7 @@ If the user picked an appetite threshold below 5 in step 6, fire a second `AskUs
 - **Confirm: appetite N, with severe-impact activities prohibited** — the user explicitly accepts the trade-off. Proceed to step 7.
 - **Revise the appetite** — return to step 6 with the appetite question only.
 
-**Non-interactive (AFK) fallback** per ADR-013 Rule 6: if `AskUserQuestion` is unavailable, do NOT proceed — the warning is load-bearing (prohibits an entire risk class) and silently consuming it would normalise the prohibition. Halt with a clear "appetite < 5 selected interactively required" message for the orchestrator to drain later.
+**Non-interactive (AFK) fallback** per ADR-013 Rule 6: if `request_user_input` is unavailable, do NOT proceed — the warning is load-bearing (prohibits an entire risk class) and silently consuming it would normalise the prohibition. Halt with a clear "appetite < 5 selected interactively required" message for the orchestrator to drain later.
 
 ### 7. Validate draft with risk-scorer agent
 

package/skills/wip/SKILL.md

@@ -1,3 +1,7 @@
+<!-- Generated from packages/risk-scorer/skills/*/SKILL.md by packages/risk-scorer/scripts/sync-codex-skills.mjs during npm pack. Do not edit packaged output directly. -->
+
+> Codex runtime note: use `request_user_input` where this skill needs structured user input. If a step refers to Claude-style agent dispatch or `subagent_type`, invoke the matching installed Codex agent when available; in `codex exec` or any runtime without custom-agent dispatch, perform the same review inline from the plugin's sibling `agents/*.md` instructions and preserve the structured verdict blocks.
+
 ---
 name: wr-risk-scorer:wip
 description: Invokable SKILL wrapper around the wr-risk-scorer:wip nudge agent. Delegates to the agent via the Agent tool and returns the agent's structured WIP risk verdict. Internal-use plumbing used by `/wr-risk-scorer:assess-wip` per ADR-015's Confirmation literal phrasing. End users should invoke `/wr-risk-scorer:assess-wip` instead.

package/skills/assess-inbound-report/test/assess-inbound-report-contract.bats

@@ -1,132 +0,0 @@
-#!/usr/bin/env bats
-# Contract assertions for /wr-risk-scorer:assess-inbound-report skill
-# (RFC-004 Slice B — on-demand wrapper per ADR-015). Peer of
-# /wr-risk-scorer:assess-external-comms.
-#
-# Structural assertions — Permitted Exception to the source-grep ban
-# per ADR-005 / P011 / ADR-037 / ADR-052 § Surface 2. SKILL.md prose
-# governs LLM-driven runtime behaviour; behavioural-replay testing
-# requires a synthetic agent harness (P012 / P176). Until that harness
-# lands, contract bats assert the load-bearing contract elements are
-# present so future edits don't silently strip them.
-#
-# @problem P079
-# @rfc RFC-004 (Slice B)
-# @adr ADR-062 (sibling subagent + on-demand wrapper)
-# @adr ADR-015 (on-demand assessment skills — § Scope table extended)
-# @adr ADR-044 (decision-delegation — taste / silent-mechanical authority)
-# @jtbd JTBD-005 (invoke governance assessments on demand)
-# @jtbd JTBD-202 (pre-flight governance checks before release/handover)
-# @jtbd JTBD-001 (mechanical-stage carve-out on pipeline pre-satisfier path)
-
-setup() {
-  SKILL_DIR="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)"
-  SKILL_FILE="${SKILL_DIR}/SKILL.md"
-  ADR_015="$(cd "${SKILL_DIR}/../../../.." && pwd)/docs/decisions/015-on-demand-assessment-skills.proposed.md"
-}
-
-@test "SKILL.md exists and has frontmatter" {
-  [ -f "$SKILL_FILE" ]
-  run head -1 "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-  [ "$output" = "---" ]
-}
-
-@test "frontmatter name is wr-risk-scorer:assess-inbound-report" {
-  run grep -nE '^name: wr-risk-scorer:assess-inbound-report$' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "frontmatter allowed-tools includes Skill (delegates to subagent)" {
-  # ADR-015 § Gate Marker Interaction: on-demand skills MUST delegate
-  # via Skill tool; never write markers directly.
-  run grep -nE '^allowed-tools:.*Skill' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "frontmatter allowed-tools includes AskUserQuestion (manual-mode step 6)" {
-  # Step 6 (manual invocation only — silent on pipeline pre-satisfier
-  # invocations per P132) uses AskUserQuestion to surface next-step
-  # options.
-  run grep -nE '^allowed-tools:.*AskUserQuestion' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "frontmatter allowed-tools includes Bash (gh issue fetch in step 2)" {
-  # Step 2 can call `gh issue view --json body,author,labels` to fetch
-  # the report body when only a URL/ref is supplied.
-  run grep -nE '^allowed-tools:.*Bash' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Delegation to the sibling subagent (NOT marker self-writes)
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "skill delegates to wr-risk-scorer:inbound-report subagent" {
-  run grep -nE 'wr-risk-scorer:inbound-report' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "skill MUST NOT write to /tmp/ markers directly (ADR-009 + ADR-015 boundary)" {
-  # PostToolUse:Agent hook (risk-score-mark.sh) owns marker writes per
-  # ADR-009 + ADR-015 § Gate Marker Interaction.
-  run grep -inE 'NOT write.*/tmp|PostToolUse hook' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Mechanical-stage carve-out: pipeline pre-satisfier path is silent
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "skill names the mechanical-stage carve-out (P132) for pipeline pre-satisfier path" {
-  run grep -inE 'P132|mechanical-stage carve-out' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "step 6 AskUserQuestion fires ONLY on manual invocation (not pipeline pre-satisfier)" {
-  # The carve-out is the load-bearing protection for JTBD-001 + JTBD-006
-  # against inverse-P078 drift. The pipeline pre-satisfier path MUST be
-  # silent on this step. Match the contract in either direction:
-  #   manual-only firing OR pipeline-pre-satisfier silent-on-step.
-  run grep -inE 'invoked manually.*pre-flight|manual only|silent on this step|silent on.*pipeline pre-satisfier' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Persona anchors (JTBD-005 + JTBD-202)
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "skill cites JTBD-005 (invoke on demand) as primary persona driver" {
-  run grep -nE 'JTBD-005' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-@test "skill cites JTBD-202 (pre-flight governance checks) as secondary persona driver" {
-  run grep -nE 'JTBD-202' "$SKILL_FILE"
-  [ "$status" -eq 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# ADR-015 Scope table row exists for assess-inbound-report
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "ADR-015 Scope table includes the assess-inbound-report row" {
-  [ -f "$ADR_015" ]
-  run grep -nE '`assess-inbound-report`' "$ADR_015"
-  [ "$status" -eq 0 ]
-  run grep -nE '`wr-risk-scorer:inbound-report`' "$ADR_015"
-  [ "$status" -eq 0 ]
-}
-
-@test "ADR-015 Confirmation checkbox covers assess-inbound-report skill" {
-  run grep -nE '\[x\] `packages/risk-scorer/skills/assess-inbound-report/SKILL\.md` created' "$ADR_015"
-  [ "$status" -eq 0 ]
-}
-
-@test "ADR-015 Related section names ADR-062 + P079 (driver references)" {
-  run grep -nE 'ADR-062.*inbound|inbound.*ADR-062' "$ADR_015"
-  [ "$status" -eq 0 ]
-  run grep -nE 'P079' "$ADR_015"
-  [ "$status" -eq 0 ]
-}

package/skills/assess-release/test/assess-skills-delegate-via-skill-tool.bats

@@ -1,162 +0,0 @@
-#!/usr/bin/env bats
-# Contract guard: the on-demand assessment SKILLs (assess-release, assess-wip,
-# assess-external-comms) MUST delegate to their scoring agent via the Skill
-# tool — not via the Agent tool — matching ADR-015's Confirmation literal
-# phrasing ("the skill delegates to wr-risk-scorer:<agent> via the Skill
-# tool"). Closes the P205 contradiction surfaced by ADR-015 Confirmation
-# vs. SKILL.md prose mismatch.
-#
-# Structural assertions — Permitted Exception to the source-grep ban
-# (ADR-005 / P011), same framing as risk-scorer-register-hint.bats. SKILL.md
-# prose IS the contract document the orchestrator (Claude) consumes when
-# executing the SKILL; an LLM-output behavioural check is out of scope for
-# bats and is the responsibility of the promptfoo harness (ADR-075).
-#
-# What is asserted (contract, not implementation):
-#   1. Each assess-* SKILL's step 5 (release) / step 3 (wip) / step 4
-#      (external-comms) names `skill:` as the delegation tool parameter
-#      with the correct wrapper SKILL name as the target.
-#   2. None of the assess-* SKILLs name `subagent_type:` as the delegation
-#      tool parameter (the P205 contradiction class).
-#   3. Each wrapper SKILL (`pipeline`, `wip`, `external-comms`) exists at
-#      its expected path, is namespaced `wr-risk-scorer:<name>`, and
-#      delegates to its sibling agent via `subagent_type:`.
-#
-# Cross-reference:
-#   P205:    docs/problems/known-error/205-wr-risk-scorer-assess-release-skill-md-step-5-prose-says-skill-tool-but-provides-subagent-type.md
-#   ADR-015: docs/decisions/015-on-demand-assessment-skills.proposed.md (Confirmation criteria 189-193)
-#   ADR-052: docs/decisions/052-behavioural-tests-default.proposed.md (Permitted Exception)
-#   @jtbd JTBD-005 (invoke governance assessments on demand)
-#   @jtbd JTBD-101 (extend the suite — plugins expose corresponding skills)
-
-setup() {
-  SKILLS_DIR="$(cd "$(dirname "$BATS_TEST_FILENAME")/../.." && pwd)"
-
-  ASSESS_RELEASE="${SKILLS_DIR}/assess-release/SKILL.md"
-  ASSESS_WIP="${SKILLS_DIR}/assess-wip/SKILL.md"
-  ASSESS_EXTERNAL_COMMS="${SKILLS_DIR}/assess-external-comms/SKILL.md"
-
-  WRAPPER_PIPELINE="${SKILLS_DIR}/pipeline/SKILL.md"
-  WRAPPER_WIP="${SKILLS_DIR}/wip/SKILL.md"
-  WRAPPER_EXTERNAL_COMMS="${SKILLS_DIR}/external-comms/SKILL.md"
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Consumer SKILLs delegate via Skill tool (skill: parameter)
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "assess-release delegates via skill: wr-risk-scorer:pipeline" {
-  [ -f "$ASSESS_RELEASE" ]
-  run grep -E "^skill: wr-risk-scorer:pipeline$" "$ASSESS_RELEASE"
-  [ "$status" -eq 0 ]
-}
-
-@test "assess-release does NOT use subagent_type: in its delegation block" {
-  [ -f "$ASSESS_RELEASE" ]
-  # The P205 contradiction was: prose says "Skill tool" but provides
-  # subagent_type: wr-risk-scorer:pipeline. After the fix, no
-  # `subagent_type:` line may appear in the delegation block.
-  run grep -E "^subagent_type: wr-risk-scorer:pipeline$" "$ASSESS_RELEASE"
-  [ "$status" -ne 0 ]
-}
-
-@test "assess-wip delegates via skill: wr-risk-scorer:wip" {
-  [ -f "$ASSESS_WIP" ]
-  run grep -E "^skill: wr-risk-scorer:wip$" "$ASSESS_WIP"
-  [ "$status" -eq 0 ]
-}
-
-@test "assess-wip does NOT use subagent_type: in its delegation block" {
-  [ -f "$ASSESS_WIP" ]
-  run grep -E "^subagent_type: wr-risk-scorer:wip$" "$ASSESS_WIP"
-  [ "$status" -ne 0 ]
-}
-
-@test "assess-external-comms delegates via skill: wr-risk-scorer:external-comms" {
-  [ -f "$ASSESS_EXTERNAL_COMMS" ]
-  run grep -E "^skill: wr-risk-scorer:external-comms$" "$ASSESS_EXTERNAL_COMMS"
-  [ "$status" -eq 0 ]
-}
-
-@test "assess-external-comms does NOT use subagent_type: in its delegation block" {
-  [ -f "$ASSESS_EXTERNAL_COMMS" ]
-  run grep -E "^subagent_type: wr-risk-scorer:external-comms$" "$ASSESS_EXTERNAL_COMMS"
-  [ "$status" -ne 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Wrapper SKILLs exist with correct names and delegate to the agent
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "wrapper SKILL packages/risk-scorer/skills/pipeline/SKILL.md exists" {
-  [ -f "$WRAPPER_PIPELINE" ]
-}
-
-@test "wrapper SKILL pipeline declares name: wr-risk-scorer:pipeline" {
-  [ -f "$WRAPPER_PIPELINE" ]
-  run grep -E "^name: wr-risk-scorer:pipeline$" "$WRAPPER_PIPELINE"
-  [ "$status" -eq 0 ]
-}
-
-@test "wrapper SKILL pipeline delegates to the pipeline agent via subagent_type:" {
-  [ -f "$WRAPPER_PIPELINE" ]
-  run grep -E "^subagent_type: wr-risk-scorer:pipeline$" "$WRAPPER_PIPELINE"
-  [ "$status" -eq 0 ]
-}
-
-@test "wrapper SKILL packages/risk-scorer/skills/wip/SKILL.md exists" {
-  [ -f "$WRAPPER_WIP" ]
-}
-
-@test "wrapper SKILL wip declares name: wr-risk-scorer:wip" {
-  [ -f "$WRAPPER_WIP" ]
-  run grep -E "^name: wr-risk-scorer:wip$" "$WRAPPER_WIP"
-  [ "$status" -eq 0 ]
-}
-
-@test "wrapper SKILL wip delegates to the wip agent via subagent_type:" {
-  [ -f "$WRAPPER_WIP" ]
-  run grep -E "^subagent_type: wr-risk-scorer:wip$" "$WRAPPER_WIP"
-  [ "$status" -eq 0 ]
-}
-
-@test "wrapper SKILL packages/risk-scorer/skills/external-comms/SKILL.md exists" {
-  [ -f "$WRAPPER_EXTERNAL_COMMS" ]
-}
-
-@test "wrapper SKILL external-comms declares name: wr-risk-scorer:external-comms" {
-  [ -f "$WRAPPER_EXTERNAL_COMMS" ]
-  run grep -E "^name: wr-risk-scorer:external-comms$" "$WRAPPER_EXTERNAL_COMMS"
-  [ "$status" -eq 0 ]
-}
-
-@test "wrapper SKILL external-comms delegates to the external-comms agent via subagent_type:" {
-  [ -f "$WRAPPER_EXTERNAL_COMMS" ]
-  run grep -E "^subagent_type: wr-risk-scorer:external-comms$" "$WRAPPER_EXTERNAL_COMMS"
-  [ "$status" -eq 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Wrapper SKILLs disambiguate from end-user assess-* surfaces
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "wrapper pipeline description names assess-release as the end-user surface" {
-  [ -f "$WRAPPER_PIPELINE" ]
-  # JTBD-005 persona-fit: solo developer must not land on the raw wrapper
-  # and miss the assess-* gate-satisfaction wrap-up. Description must
-  # disambiguate.
-  run grep -E "assess-release" "$WRAPPER_PIPELINE"
-  [ "$status" -eq 0 ]
-}
-
-@test "wrapper wip description names assess-wip as the end-user surface" {
-  [ -f "$WRAPPER_WIP" ]
-  run grep -E "assess-wip" "$WRAPPER_WIP"
-  [ "$status" -eq 0 ]
-}
-
-@test "wrapper external-comms description names assess-external-comms as the end-user surface" {
-  [ -f "$WRAPPER_EXTERNAL_COMMS" ]
-  run grep -E "assess-external-comms" "$WRAPPER_EXTERNAL_COMMS"
-  [ "$status" -eq 0 ]
-}

package/skills/bootstrap-catalog/test/bootstrap-catalog.bats

@@ -1,168 +0,0 @@
-#!/usr/bin/env bats
-# Doc-lint guard: /wr-risk-scorer:bootstrap-catalog SKILL.md MUST define
-# the runtime contract per ADR-059 verdicts A4 (on-demand surface) +
-# B1 (slug dedupe) + C1 (no threshold) + D1 (Source Evidence required).
-#
-# Structural assertions — Permitted Exception to the source-grep ban (ADR-005 / P011).
-# SKILL.md is a specification document; behavioural verification of LLM-driven
-# skills is out of scope for bats. The contract document is what consuming
-# orchestrators (install-updates Step 6.5.1 auto-trigger) rely on.
-#
-# Cross-reference:
-#   ADR-059: docs/decisions/059-pipeline-consume-catalog-and-bootstrap-from-reports.proposed.md
-#   ADR-056: docs/decisions/056-risk-register-back-channel-write-contract.proposed.md (slug primitive)
-#   ADR-026: docs/decisions/026-agent-output-grounding.proposed.md (sentinel)
-#   ADR-047: docs/decisions/047-install-updates-scaffolds-governance-artefacts.proposed.md (parent)
-#   P168:    docs/problems/168-risk-scorer-doesnt-consume-catalog-or-bootstrap.known-error.md
-#   @jtbd JTBD-001 (enforce governance without slowing down — bootstrap eliminates miss-rate gap)
-#   @jtbd JTBD-006 (AFK-safety — bootstrap is idempotent + non-interactive)
-#   @jtbd JTBD-202 (pre-flight governance — catalog as ISO 31000/27001 audit-trail)
-
-setup() {
-  SKILL_DIR="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)"
-  SKILL="${SKILL_DIR}/SKILL.md"
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Frontmatter: name, description, allowed-tools, maturity
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "bootstrap-catalog SKILL.md has frontmatter with correct namespaced name" {
-  run grep -qE "^name: wr-risk-scorer:bootstrap-catalog" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-@test "bootstrap-catalog SKILL.md frontmatter declares Write tool" {
-  run grep -qE "^allowed-tools:.*Write" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-@test "bootstrap-catalog SKILL.md frontmatter declares maturity per ADR-053" {
-  run grep -qE "^maturity: (proposed|accepted|recommended)" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Pre-conditions (Step 0): RISK-POLICY.md present, docs/risks/ scaffolded, .risk-reports/ non-empty
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "bootstrap-catalog SKILL.md requires RISK-POLICY.md presence" {
-  run grep -qE "RISK-POLICY.md.*present|requires.*RISK-POLICY" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-@test "bootstrap-catalog SKILL.md owns docs/risks/ directory lifecycle (no separate scaffold required)" {
-  # Updated 2026-05-05: the previous "requires scaffold" assertion is obsolete.
-  # Per user direction 2026-05-04 (commit 8edaf7b), the Phase 1 scaffold step
-  # + TEMPLATE.md were wiped because the scaffolded entries were wrong content;
-  # bootstrap-catalog now owns the directory's full lifecycle (mkdir -p on demand,
-  # writes README + per-slug entries, no separate scaffold step required).
-  # The SKILL.md was rewritten accordingly; this test now asserts the new contract.
-  run grep -qE "may or may not exist|creates it on demand|owns the directory's full lifecycle" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-@test "bootstrap-catalog SKILL.md requires .risk-reports/ corpus non-empty" {
-  run grep -qE "[.]risk-reports/.*non-empty|[.]risk-reports/.*at least one" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Slug dedupe per ADR-056
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "bootstrap-catalog SKILL.md cites ADR-056 for slug primitive" {
-  run grep -q "ADR-056" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-@test "bootstrap-catalog SKILL.md describes dedupe-by-slug per ADR-056" {
-  run grep -qE "[Dd]edupe by slug|dedupe.*slug|slug is the dedupe key|N reports.*same slug.*ONE" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# No threshold (Verdict C1)
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "bootstrap-catalog SKILL.md emits one entry per unique slug (no frequency floor)" {
-  run grep -qE "one R<NNN>-<slug>[.]active[.]md per unique slug|one .*per unique slug" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Source Evidence block required (Verdict D1)
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "bootstrap-catalog SKILL.md requires Source Evidence block on new entries" {
-  run grep -q "## Source Evidence" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-@test "bootstrap-catalog SKILL.md cites originating .risk-reports/ files in Source Evidence" {
-  run grep -qE "originating reports|originating.*[.]risk-reports/|cite.*[.]risk-reports/" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-@test "bootstrap-catalog SKILL.md cites ADR-026 grounding for Source Evidence pattern" {
-  run grep -qE "ADR-026.*grounding|grounding.*ADR-026" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# ADR-026 sentinel for ungrounded scoring fields
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "bootstrap-catalog SKILL.md uses ADR-026 sentinel for ungrounded scoring" {
-  run grep -q "not estimated — no prior data" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-@test "bootstrap-catalog SKILL.md sets pending-review Status on auto-scaffolded entries" {
-  run grep -q "Active (auto-scaffolded — pending review)" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Idempotency contract
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "bootstrap-catalog SKILL.md describes idempotency via file-existence per slug" {
-  run grep -qE "[Ii]dempotent|file-existence|file existence test|re-run produces zero diff|safe to invoke at any time" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-@test "bootstrap-catalog SKILL.md handles slug collision via Source Evidence append" {
-  run grep -qE "[Mm]atch exists.*append|slug collision|append.*Source Evidence" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Empty corpus / no reports handling
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "bootstrap-catalog SKILL.md exits cleanly when .risk-reports/ is empty" {
-  run grep -qE "no-op|exit cleanly.*no.*reports|nothing to walk|empty.*[Bb]ootstrap.*no-op" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Commit per ADR-014 single-commit grain
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "bootstrap-catalog SKILL.md cites ADR-014 single-commit grain" {
-  run grep -q "ADR-014" "$SKILL"
-  [ "$status" -eq 0 ]
-}
-
-# ──────────────────────────────────────────────────────────────────────────────
-# Pure-scorer carve-out: this skill needs Write tool (it's the writer)
-# ──────────────────────────────────────────────────────────────────────────────
-
-@test "bootstrap-catalog SKILL.md is the orchestrator-side write surface (per Verdict G)" {
-  # ADR-059 verdict G: bootstrap-catalog skill needs Write tool; pipeline agent
-  # stays Read+Glob only (pure-scorer contract preserved). This skill's Write
-  # grant is the legitimate orchestrator-side write surface.
-  run grep -qE "needs Write tool|orchestrator-side|on-demand surface|Verdict G" "$SKILL"
-  [ "$status" -eq 0 ]
-}