agentic-sdlc-wizard 1.60.0 → 1.61.0

package/.claude-plugin/marketplace.json

@@ -13,7 +13,7 @@
       "name": "sdlc-wizard",
       "source": ".",
       "description": "SDLC enforcement for AI agents — TDD, planning, self-review, CI shepherd",
-      "version": "1.60.0",
+      "version": "1.61.0",
       "author": {
         "name": "Stefan Ayala"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "sdlc-wizard",
-  "version": "1.60.0",
+  "version": "1.61.0",
   "description": "SDLC enforcement for AI agents — TDD, planning, self-review, CI shepherd",
   "author": {
     "name": "Stefan Ayala",

package/CHANGELOG.md

@@ -4,6 +4,33 @@ All notable changes to the SDLC Wizard.
 
 > **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.
 
+## [1.61.0] - 2026-04-30
+
+### Added
+
+- **Calibration scenario suite — closes ROADMAP #96 Phase 3 PR 2.** New `tests/e2e/scenarios/calibration-careful-read.md` is the first scenario in a new `calibration-*` family designed specifically to reward self-review and punish rushed implementations. Builds on PR 1 (the lift-proof harness, v1.60.0).
+
+  The scenario asks the agent to add a `parsePrice(input)` utility that handles five distinct formats (standard, cents-only, comma thousand-separator, surrounding whitespace, invalid). A self-reviewing agent reads all five requirements before coding; a rushed agent skims the first example and ships `parseFloat(s.replace('$', ''))` — which silently corrupts `'$1,000.00'` to `1` (a thousand-fold pricing bug). The score delta between these two agent profiles on this scenario is a load-bearing **calibration signal** for `lift-proof.sh`.
+
+  Out of scope: actual end-to-end calibration verification (does a low-effort agent actually score lower on this scenario than an xhigh agent?). That's deferred to ROADMAP #212(i) Prove-It Gate paired runs. PR 2 ships the scenario; #212(i) runs the comparison.
+
+### Tests
+
+- New `tests/test-calibration-scenarios.sh` (6 tests): asserts a `calibration-*.md` exists, has the standard scenario format (`# Scenario:`, `## Task`, `## Fixture:`, calibration-signal docs), and lists ≥2 numbered requirements (the careful-read multi-path signal).
+- Wired into `ci.yml` and `CONTRIBUTING.md` test list.
+
+### Files
+
+- `tests/e2e/scenarios/calibration-careful-read.md` (new) — the parsePrice scenario
+- `tests/test-calibration-scenarios.sh` (new) — format validator
+- `.github/workflows/ci.yml` — new test step
+- `CONTRIBUTING.md` — test list parity
+- `CHANGELOG.md`, `ROADMAP.md`, `SDLC.md`, `CLAUDE_CODE_SDLC_WIZARD.md`, `skills/update/SKILL.md`, `package.json`, `.claude-plugin/plugin.json` + `marketplace.json` (1.60.0 → 1.61.0)
+
+### What's still TBD
+
+The `calibration-*` family is intentionally extensible. Future scenarios could test other SDLC virtues — scope guard (don't fix things outside the task), TDD discipline (write tests before implementation), regression hygiene (don't break existing tests). Each new calibration scenario is a separate PR; PR 2 establishes the format.
+
 ## [1.60.0] - 2026-04-30
 
 ### Added

package/CLAUDE_CODE_SDLC_WIZARD.md

@@ -2974,7 +2974,7 @@ If deployment fails or post-deploy verification catches issues:
 
 **SDLC.md:**
 ```markdown
-<!-- SDLC Wizard Version: 1.60.0 -->
+<!-- SDLC Wizard Version: 1.61.0 -->
 <!-- Setup Date: [DATE] -->
 <!-- Completed Steps: step-0.1, step-0.2, step-0.4, step-1, step-2, step-3, step-4, step-5, step-6, step-7, step-8, step-9 -->
 <!-- Git Workflow: [PRs or Solo] -->
@@ -4039,7 +4039,7 @@ Walk through updates? (y/n)
 Store wizard state in `SDLC.md` as metadata comments (invisible to readers, parseable by Claude):
 
 ```markdown
-<!-- SDLC Wizard Version: 1.60.0 -->
+<!-- SDLC Wizard Version: 1.61.0 -->
 <!-- Setup Date: 2026-01-24 -->
 <!-- Completed Steps: step-0.1, step-0.2, step-1, step-2, step-3, step-4, step-5, step-6, step-7, step-8, step-9 -->
 <!-- Git Workflow: PRs -->

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentic-sdlc-wizard",
-  "version": "1.60.0",
+  "version": "1.61.0",
   "description": "SDLC enforcement for Claude Code — hooks, skills, and wizard setup in one command",
   "bin": {
     "sdlc-wizard": "cli/bin/sdlc-wizard.js"

package/skills/update/SKILL.md

@@ -93,9 +93,10 @@ Parse CHANGELOG entries between the user's installed version and latest. Present
 
 ```
 Installed: 1.42.0
-Latest:    1.60.0
+Latest:    1.61.0
 
 What changed:
+- [1.61.0] calibration scenarios for #96 Phase 3 PR 2 — `tests/e2e/scenarios/calibration-careful-read.md` (parsePrice with 5 edge-case formats) tests whether self-review catches missed requirements. Score delta between SDLC and naive agents on this scenario is a calibration signal for `lift-proof.sh`
 - [1.60.0] wizard-installation lift-proof harness (#96 Phase 3 PR 1) — `tests/e2e/lift-proof.sh` runs same scenario on bare vs wizard-installed fixture, emits score delta. Closes the "does the wizard work?" question. Honestly zero-API (sim + eval on Max)
 - [1.59.0] evaluator on Max via `claude --print` (#228) — `EVAL_USE_CLI=1` swaps `evaluate.sh`'s per-criterion judge transport from `curl` → API to `claude --print --output-format json`. local-shepherd.sh sets it by default, so the local path is honestly zero-API
 - [1.58.0] ground-truth gate for E2E benchmark (#96 Phase 2) — `tests/e2e/ground-truth.sh` runs `npm test` post-sim; final score capped at 5 if tests fail. Catches "agent followed protocol but produced broken code"