@windyroad/retrospective 0.13.0-preview.263 → 0.14.0-preview.265

package/.claude-plugin/plugin.json

@@ -1,5 +1,5 @@
 {
   "name": "wr-retrospective",
-  "version": "0.13.0",
+  "version": "0.14.0",
   "description": "Session retrospective reminders and plan review for Claude Code"
 }

package/bin/wr-retrospective-check-skill-md-budgets

@@ -0,0 +1,2 @@
+#!/usr/bin/env bash
+exec "$(dirname "$0")/../scripts/check-skill-md-budgets.sh" "$@"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@windyroad/retrospective",
-  "version": "0.13.0-preview.263",
+  "version": "0.14.0-preview.265",
   "description": "Session retrospectives that update briefings and create problem tickets",
   "bin": {
     "windyroad-retrospective": "./bin/install.mjs"

package/skills/run-retro/SKILL.md

@@ -163,7 +163,7 @@ The shape mirrors P068's Step 4a Verification-close housekeeping: glob / evidenc
 
 - **Step 4a (Verification-close housekeeping, P068)** — same evidence-scan shape applied to a different surface. Both share the glob / scan / categorise / specific-citation / interactive-or-AFK pattern. Step 4a scans for successful exercise of `.verifying.md` fixes; Step 2b scans for tool-level friction. They fire independently and produce independent retro-summary sections.
 - **Step 4 (problem-ticket creation)** — Step 2b feeds Step 4. A detection surfaced in Step 2b that the user accepts becomes a Step 4 creation or update via the manage-problem delegation. Step 4b's Stage 1 two-stage codification flow (P075) applies to pipeline-instability tickets the same way it applies to Step 2 reflection tickets — the detection IS the codify-worthy observation.
-- **ADR-027 compatibility note**: when ADR-027's Step-0 auto-delegation lands on run-retro, Step 2b's evidence scan is load-bearing on main-agent session context that a delegated subagent does not automatically inherit. The migration path mirrors Step 4a's: either (a) run Step 2b in the main-agent context BEFORE Step-0 delegation to the subagent, or (b) include an explicit session-activity summary (tool invocations, commits, skill calls observed in main-agent context) in the Step-0 delegation prompt. Option (a) is preferred to keep the evidence scan close to the observed activity.
+- **ADR-032 supersession note** (was: ADR-027 compatibility note): ADR-027's Step-0 subagent auto-delegation has been superseded by **ADR-032** (Governance skill invocation patterns). No Step-0 subagent migration applies to run-retro under ADR-032's foreground-synchronous pattern — Step 2b's evidence scan executes directly in main-agent context, where the session's tool-call history is natively visible. The hypothetical session-activity-summary marshalling this note previously discussed is obviated by the supersession; preserved here as audit-trail continuity for prior cross-references.
 
 ### 2c. Context-usage measurement (cheap layer, P101)
 
@@ -209,7 +209,7 @@ Per **ADR-043** (Progressive context-usage measurement and reporting for retrosp
 - **`P105` signal-vs-noise pass** (Step 1.5 of this skill) — measures **per-entry** signal scores on briefing entries. The cheap layer's `briefing` bucket is upstream of the per-entry signal scores; deep layer cites both as evidence sources.
 - **Step 4 / 4b — codification flow**: when the cheap layer surfaces a delta-from-prior anomaly that the user wants to investigate, the deep layer (`/wr-retrospective:analyze-context`) is the correct routing target — it produces a `docs/retros/<date>-context-analysis.md` report with per-turn attribution and suggestion generation. The cheap layer never auto-routes.
 - **`/wr-retrospective:analyze-context` (deep layer)** — invoked only by explicit user direction. Never auto-fires from this step. Deep-layer report writes the HTML-comment-trailer snapshot that subsequent runs of this step read.
-- **ADR-027 compatibility note**: same migration shape as Step 2b. The script invocation must run in main-agent context; the parsed bucket totals are the artefact a delegated subagent can consume without re-running the byte-count.
+- **ADR-032 supersession note** (was: ADR-027 compatibility note): no Step-0 subagent migration applies — under ADR-032's foreground-synchronous pattern the script invocation runs in main-agent context as written. The migration shape this note previously discussed is obviated by the supersession.
 
 ### 2d. Ask Hygiene Pass (P135 Phase 5 / ADR-044)
 
@@ -374,7 +374,7 @@ Problems whose fix shipped but whose closure is still pending (`docs/problems/*.
 
 8. **Same-session verifyings excluded** (unchanged from P068 design): `.verifying.md` tickets for fixes that ship in the currently-running session (e.g. P127, P065, P126, P101 just transitioned this session) are NOT close-candidates — a session cannot verify its own fix beyond "bats passed at commit time"; subsequent-session exercise is the meaningful signal. Same-session verifyings are skipped in step 4 categorisation.
 
-**ADR-027 compatibility note**: when ADR-027's Step-0 auto-delegation lands on run-retro (run-retro is named in ADR-027's Scope as in-scope but has no Step 0 today), the evidence scan in step 3 becomes load-bearing on main-agent session context that a delegated subagent does not automatically inherit. The SKILL.md contract for that migration: either (a) run Step 4a in the main-agent context BEFORE Step-0 delegation to the subagent, or (b) have the Step-0 delegation prompt include an explicit session-activity summary (tool invocations, commits, skill calls observed in main-agent context) so the subagent has citable evidence. Option (a) is preferred because it keeps the evidence scan as close as possible to the observed activity; option (b) is the fallback if the subagent boundary must be crossed first.
+**ADR-032 supersession note** (was: ADR-027 compatibility note): ADR-027's Step-0 subagent auto-delegation was superseded by **ADR-032** (Governance skill invocation patterns). No Step-0 subagent migration applies to run-retro — Step 4a's evidence scan runs directly in main-agent context, where session-activity citations are natively grounded per ADR-026. The hypothetical session-activity-summary marshalling this note previously discussed is obviated by the supersession; preserved here as audit-trail continuity for prior cross-references.
 
 **Interaction with other surfaces**:
 - **manage-problem Step 9d** (baseline user-initiated verification review per P048) still fires on `/wr-itil:manage-problem review` — it is the age-based heuristic path. Step 4a here is the evidence-based session-wrap path. The two compose: a ticket that is both "≥ 14 days old" (Step 9d highlight) AND "exercised successfully this session" (Step 4a candidate) should be surfaced in both paths independently; closing via either path moves the ticket to `.closed.md` and de-lists it from both queues.

package/skills/run-retro/test/run-retro-pipeline-instability-scan.bats

@@ -80,8 +80,15 @@ setup() {
   [ "$status" -eq 0 ]
 }
 
-@test "run-retro: Step 2b ADR-027 compatibility note documents subagent-context handling" {
-  run grep -F 'ADR-027' "$SKILL_MD"
+@test "run-retro: Step 2b ADR-032 supersession note documents post-supersession context handling" {
+  # ADR-027 was superseded by ADR-032 (2026-04-21). The former
+  # "ADR-027 compatibility note" was rewritten to an ADR-032 supersession
+  # note that records the obviation of any Step-0 subagent migration.
+  # Structural grep retained for now (P081 anti-pattern; convert to
+  # behavioural fixture in a follow-up — tracked separately).
+  run grep -F 'ADR-032 supersession note' "$SKILL_MD"
+  [ "$status" -eq 0 ]
+  run grep -F 'No Step-0 subagent migration applies' "$SKILL_MD"
   [ "$status" -eq 0 ]
 }
 

package/skills/run-retro/test/run-retro-verification-close-housekeeping.bats

@@ -90,10 +90,15 @@ setup() {
   [[ "$output" != *"Close P<NNN>\` — description"* ]]
 }
 
-@test "run-retro: Step 4a ADR-027 compatibility note documents session-context handling" {
-  run grep -F 'ADR-027 compatibility note' "$SKILL_MD"
-  [ "$status" -eq 0 ]
-  run grep -F 'subagent' "$SKILL_MD"
+@test "run-retro: Step 4a ADR-032 supersession note documents post-supersession context handling" {
+  # ADR-027 was superseded by ADR-032 (2026-04-21). The former
+  # "ADR-027 compatibility note" was rewritten to an ADR-032 supersession
+  # note that records the obviation of any Step-0 subagent migration.
+  # Structural grep retained for now (P081 anti-pattern; convert to
+  # behavioural fixture in a follow-up — tracked separately).
+  run grep -F 'ADR-032 supersession note' "$SKILL_MD"
+  [ "$status" -eq 0 ]
+  run grep -F 'No Step-0 subagent migration applies' "$SKILL_MD"
   [ "$status" -eq 0 ]
 }