agentic-sdlc-wizard 1.85.0 → 1.87.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: update-wizard
3
3
  description: Smart update for SDLC wizard — shows changelog, compares files, lets you selectively adopt changes while preserving customizations.
4
- argument-hint: [optional: check-only | force-all]
4
+ argument-hint: "[optional: check-only | force-all]"
5
5
  effort: high
6
6
  ---
7
7
  # Update Wizard - Smart SDLC Update
@@ -95,16 +95,15 @@ Parse CHANGELOG entries between the user's installed version and the resolved la
95
95
 
96
96
  ```
97
97
  Installed: 1.42.0
98
- Latest: 1.85.0
98
+ Latest: 1.87.0
99
99
 
100
100
  What changed:
101
- - [1.85.0] Post-ship retrospective fixes: CI Feedback Loop synced to SKILL.md's stronger version (NEVER AUTO-MERGE, read-logs-even-when-green, cross-model CI audit), CERTIFIED≠CI lesson, Policy Migration Inventory checklist, stale round-count correction (#437 hook-staleness fix follows separately).
101
+ - [1.87.0] First external contribution (@thejesh23, #444): argument-hint frontmatter quoted so Copilot CLI ≥1.0.65 loads skills, plus regression test; GPT-5.6 Sol reviewer sweep; Sonnet 5 default effort medium (unbacked 5x quota claim removed, hook floor matched).
102
+ - [1.86.0] Fix #437: codex-gate-check.sh now blocks stale certifications — a CERTIFIED handoff.json no longer sails through forever; it records commit_sha at cert time and blocks once HEAD moves past it without a re-cert.
103
+ - [1.85.0] Post-ship retrospective: CI Feedback Loop synced to SKILL.md's stronger version, CERTIFIED≠CI lesson, Policy Migration Inventory checklist, stale round-count correction.
102
104
  - [1.84.0] Hook enforcement fix: cross-model review gate + TDD RED gate now actually block (#436); model-aware effort docs replace blanket max recommendation.
103
105
  - [1.83.0] Model config batch: multi-model hook recommendation (#403), global [1m] pin detection (#391), version race fix (#405), effort config check (#384).
104
106
  - [1.82.0] Usage diagnostics: fix /usage row, Reading Usage Signals guide, advisor fallback procedure, Fable effort guidance, autocompact cross-reference.
105
- - [1.81.0] Native `advisorModel` support: Setup A gets Fable advisor, Setup B gets Opus advisor. Replaces manual subagent spawning. Requires CC v2.1.170+.
106
- - [1.80.0] Flip default: Opus 4.6 max becomes recommended flagship; Opus 4.8 demoted to opt-in `[l] Latest` tier.
107
- - [1.77.0] release-dry-run.yml + cc-version-drift.yml (#350) + /goal SDLC gates (95% + DLC binding).
108
107
  - [1.75.1] release-workflow fix — Node 22 → 24 (ships npm 11.x), dropped flaky `npm install -g` self-upgrade (hit MODULE_NOT_FOUND on v1.75.0 publish). Explicit npm-version guard.
109
108
  - [1.75.0] npm Trusted Publishing — `release.yml` swapped from `NPM_TOKEN` to OIDC. No more token rotation. Requires one-time publisher config on the npm package page.
110
109
  - [1.74.0] v1.43 salvage: #338 precedence preamble; #235ab `/insights`; codex `< /dev/null` stdin-hang fix; test env-isolation.
@@ -1,82 +0,0 @@
1
- #!/bin/bash
2
- # /goal SDLC discipline gate (ROADMAP #360).
3
- #
4
- # UserPromptSubmit hook. When the user invokes `/goal <condition>`, scan the
5
- # prior assistant text for a HIGH 95% confidence statement AND check the
6
- # condition for a DLC binding (`/sdlc`, `/gdlc`, `/ldlc`, etc.). Emit loud
7
- # warnings on either gap so the SDLC-discipline gap surfaces BEFORE the goal
8
- # evaluator starts rubber-stamping flailing as progress.
9
- #
10
- # PR #355 (v1.77.0) added the guidance text in skills/sdlc/SKILL.md. This
11
- # hook is the enforcement layer per #360. Non-blocking soft nudge — same
12
- # pattern as model-effort-check.sh.
13
-
14
- HOOK_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
15
- source "$HOOK_DIR/_find-sdlc-root.sh"
16
-
17
- # Plugin + project copies both register this hook → plugin yields (#236).
18
- dedupe_plugin_or_project "${BASH_SOURCE[0]}" || exit 0
19
-
20
- # Must be invoked via hook (stdin JSON), not interactively.
21
- [ -t 0 ] && exit 0
22
- STDIN_JSON=$(cat)
23
- [ -z "$STDIN_JSON" ] && exit 0
24
- command -v jq > /dev/null 2>&1 || exit 0
25
-
26
- PROMPT=$(printf '%s' "$STDIN_JSON" | jq -r '.prompt // empty' 2>/dev/null) || exit 0
27
- [ -z "$PROMPT" ] && exit 0
28
-
29
- # Only act on `/goal <condition>` invocations. `/goal` alone (status) and
30
- # `/goal clear` (reset) must stay silent — those aren't discipline events.
31
- case "$PROMPT" in
32
- "/goal") exit 0 ;;
33
- "/goal "[[:space:]]*) exit 0 ;;
34
- "/goal clear") exit 0 ;;
35
- "/goal clear "*) exit 0 ;;
36
- "/goal "*) ;;
37
- *) exit 0 ;;
38
- esac
39
-
40
- CONDITION="${PROMPT#/goal }"
41
-
42
- # === Confidence gate ===
43
- # Read transcript_path, slurp JSONL, find last assistant message with text
44
- # content, scan for HIGH-95% confidence pattern. Silent on missing/unreadable
45
- # transcript — better to under-warn than crash a soft nudge.
46
- TRANSCRIPT_PATH=$(printf '%s' "$STDIN_JSON" | jq -r '.transcript_path // empty' 2>/dev/null) || TRANSCRIPT_PATH=""
47
- HAS_CONFIDENCE=0
48
- if [ -n "$TRANSCRIPT_PATH" ] && [ -r "$TRANSCRIPT_PATH" ]; then
49
- LAST_ASSISTANT_TEXT=$(jq -rs '
50
- [.[] | select(.type == "assistant")]
51
- | last
52
- | if . == null then ""
53
- else (.message.content // []) | map(select(.type == "text") | .text) | join("\n")
54
- end
55
- ' "$TRANSCRIPT_PATH" 2>/dev/null) || LAST_ASSISTANT_TEXT=""
56
- if printf '%s' "$LAST_ASSISTANT_TEXT" | grep -qiE 'HIGH \(?95%|confidence:?[[:space:]]+HIGH|HIGH[[:space:]]+95%|95%[[:space:]]+confidence'; then
57
- HAS_CONFIDENCE=1
58
- fi
59
- fi
60
-
61
- if [ "$HAS_CONFIDENCE" -eq 0 ]; then
62
- echo ""
63
- echo "!! /GOAL CONFIDENCE GATE: prior turn did not state HIGH 95% confidence !!"
64
- echo " The /goal Haiku evaluator rubber-stamps flailing as progress below 95%."
65
- echo " Recommendation: /goal clear → do research → state HIGH 95% confidence → re-issue /goal."
66
- echo " (Source: skills/sdlc/SKILL.md Long-Running Goals section, ROADMAP #360.)"
67
- echo ""
68
- fi
69
-
70
- # === DLC binding gate ===
71
- # Condition MUST name a DLC (`/sdlc`, `/gdlc`, `/ldlc`, etc.) so the
72
- # evaluator anchors on "doing it right" not just "doing it".
73
- if ! printf '%s' "$CONDITION" | grep -qiE '/[a-z]+dlc'; then
74
- echo ""
75
- echo "!! /GOAL DLC-BINDING GATE: condition does not name a DLC (/sdlc, /gdlc, /ldlc) !!"
76
- echo " The evaluator needs a discipline anchor to judge 'doing it right' vs flailing."
77
- echo " Recommendation: rewrite condition to include 'following /sdlc' (or /gdlc/etc)."
78
- echo " (Source: skills/sdlc/SKILL.md Long-Running Goals section, ROADMAP #360.)"
79
- echo ""
80
- fi
81
-
82
- exit 0