agentic-sdlc-wizard 1.15.0 → 1.20.0
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.
- package/CHANGELOG.md +45 -0
- package/CLAUDE_CODE_SDLC_WIZARD.md +398 -183
- package/README.md +51 -35
- package/cli/bin/sdlc-wizard.js +14 -3
- package/cli/init.js +202 -10
- package/cli/templates/hooks/instructions-loaded-check.sh +1 -1
- package/cli/templates/hooks/sdlc-prompt-check.sh +16 -5
- package/cli/templates/skills/sdlc/SKILL.md +188 -33
- package/cli/templates/skills/setup/SKILL.md +178 -0
- package/cli/templates/skills/update/SKILL.md +141 -0
- package/package.json +1 -1
- package/cli/templates/skills/testing/SKILL.md +0 -97
package/CHANGELOG.md
CHANGED
|
@@ -4,6 +4,51 @@ All notable changes to the SDLC Wizard.
|
|
|
4
4
|
|
|
5
5
|
> **Note:** This changelog is for humans to read. Don't manually apply these changes - just run the wizard ("Check for SDLC wizard updates") and it handles everything automatically.
|
|
6
6
|
|
|
7
|
+
## [1.20.0] - 2026-03-31
|
|
8
|
+
|
|
9
|
+
### Added
|
|
10
|
+
- CC version-pinned update gate — E2E tests run actual new CC version, not bundled binary (#46)
|
|
11
|
+
- Tier 1 E2E flakiness fix — regression threshold 1.5→3.0, absorbs ±2-3 point LLM variance (#47)
|
|
12
|
+
- Flaky test prevention guidance with external reference in wizard, SKILL.md
|
|
13
|
+
- 2 release consistency tests (package.json ↔ CHANGELOG ↔ SDLC.md version parity)
|
|
14
|
+
|
|
15
|
+
## [1.19.0] - 2026-03-31
|
|
16
|
+
|
|
17
|
+
### Added
|
|
18
|
+
- CI Local Shepherd Model — two-tier CI fix model (shepherd primary, bot fallback), SHA-based suppression (#36)
|
|
19
|
+
- Gap Analysis vs `/claude-automation-recommender` — complementary tools positioning (#35)
|
|
20
|
+
- `/clear` vs `/compact` context management guidance (#38)
|
|
21
|
+
- Token efficiency auditing — `/cost`, `--max-budget-usd`, OpenTelemetry (#42)
|
|
22
|
+
- Blank repo support — verified clean install, 10 new E2E tests (#31)
|
|
23
|
+
- Feature documentation enforcement — ADR guidance, `claude-md-improver`, doc sync in SDLC (#43)
|
|
24
|
+
- Setup skill description trimmed to 199 chars (v2.1.86 caps at 250)
|
|
25
|
+
|
|
26
|
+
## [1.18.0] - 2026-03-30
|
|
27
|
+
|
|
28
|
+
### Added
|
|
29
|
+
- `/update-wizard` skill — guided update with changelog diff, per-file comparison, selective adoption
|
|
30
|
+
- `step-update-wizard` in wizard step registry
|
|
31
|
+
- CLI distributes `skills/update/SKILL.md` (now 8 managed files)
|
|
32
|
+
- `/update-wizard` reference in wizard "How to Update" section
|
|
33
|
+
|
|
34
|
+
## [1.17.0] - 2026-03-30
|
|
35
|
+
|
|
36
|
+
### Fixed
|
|
37
|
+
- Setup skill now force-reads entire wizard doc before proceeding (was just "Reference")
|
|
38
|
+
- README no longer tells users to manually invoke setup — hooks auto-invoke
|
|
39
|
+
- 3 new tests for setup auto-invoke behavior
|
|
40
|
+
|
|
41
|
+
### Changed
|
|
42
|
+
- Testing consolidation: `/testing` skill merged into `/sdlc` (#28)
|
|
43
|
+
|
|
44
|
+
## [1.16.0] - 2026-03-29
|
|
45
|
+
|
|
46
|
+
### Added
|
|
47
|
+
- Cross-model review dialogue protocol — structured FIXED/DISPUTED/ACCEPTED negotiation loop (#40)
|
|
48
|
+
- P0/P1/P2 severity rubric in PR review prompt (#34)
|
|
49
|
+
- Effort level recommendations in wizard
|
|
50
|
+
- 5 enforcement gap fixes in TodoWrite checklist (#39)
|
|
51
|
+
|
|
7
52
|
## [1.15.0] - 2026-03-25
|
|
8
53
|
|
|
9
54
|
### Added
|