claude-code-kit 0.32.0__tar.gz → 0.33.0__tar.gz

{claude_code_kit-0.32.0 → claude_code_kit-0.33.0}/.claude-plugin/marketplace.json

@@ -10,7 +10,7 @@
       "name": "claude-kit",
       "source": "./",
       "description": "Cookiecutter-style scaffolder for an autonomous Claude Code SDLC config (no app code, no Docker): install CLAUDE.md + .claude/ (rules, the profile's agents/skills, hooks, artifact templates) + optional .mcp.json, then run /sdlc to drive spec → review → build → test → security → ship through profile-aware quality gates, working memory, and a self-improving learnings loop.",
-      "version": "0.32.0",
+      "version": "0.33.0",
       "license": "MIT",
       "keywords": ["sdlc", "agents", "orchestration", "quality-gates", "workflow", "scaffold", "cookiecutter"]
     }

{claude_code_kit-0.32.0 → claude_code_kit-0.33.0}/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-kit",
-  "version": "0.32.0",
+  "version": "0.33.0",
   "description": "Cookiecutter-style scaffolder for an autonomous Claude Code SDLC config (no app code, no Docker). `claude-kit init` asks ordered questions and installs CLAUDE.md + .claude/ (rules, the profile's agents/skills, hooks, artifact templates) + optional .mcp.json; run /sdlc to drive spec → review → build → test → security → ship through profile-aware quality gates with working memory and a self-improving learnings loop.",
   "author": {
     "name": "Arjunsingh Yadav",

{claude_code_kit-0.32.0 → claude_code_kit-0.33.0}/CHANGELOG.md

@@ -4,6 +4,23 @@ All notable changes to claude-kit are documented here. The format follows
 [Keep a Changelog](https://keepachangelog.com/), and the project uses
 [semantic versioning](https://semver.org/).
 
+## [0.33.0] — 2026-06-25
+
+**Pre-code Reuse & YAGNI gate** (pattern adopted from the [ponytail](https://github.com/DietrichGebert/ponytail)
+plugin, MIT; re-derived in claude-kit's idiom, no vendored code). The kit's complexity controls were all
+*reactive* (the `over-engineering-review` skill scans bloat out after code exists). This adds the proactive
+twin:
+
+- **`rules/mandatory-workflow.md` §2a.5 — Reuse & YAGNI Gate** — a new Phase-2 stage between "read code"
+  (2a) and "write code" (2b). Before adding any new file/function/abstraction, the developer walks a
+  stop-at-first-rung ladder — *needs to exist? → already in the codebase? → stdlib? → native platform
+  feature? → existing dependency? → minimum that works?* — applying the same delete/stdlib/native/yagni/
+  shrink lenses as `over-engineering-review`, but *before* the code is written. Wired into the Quick
+  Reference flow and the pipeline-gating table.
+- **`skills/over-engineering-review/SKILL.md`** — cross-links the gate as its proactive twin.
+
+No catalog/hook/agent/count changes; existing commands unaffected.
+
 ## [0.32.0] — 2026-06-25
 
 **Two patterns adopted from Agent-Reach (MIT); no behavior change to existing commands.**

{claude_code_kit-0.32.0 → claude_code_kit-0.33.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: claude-code-kit
-Version: 0.32.0
+Version: 0.33.0
 Summary: Cookiecutter-style scaffolder for an autonomous Claude Code SDLC configuration (no app code, no Docker). Asks ordered questions and installs CLAUDE.md + .claude/ (rules, the chosen profile's agents/skills, hooks, artifact templates) + optional .mcp.json; run /sdlc to drive spec → review → build → test → security → ship through profile-aware quality gates, working memory, and a self-improving learnings loop.
 Project-URL: Homepage, https://github.com/ajyadav013/claude-kit
 Project-URL: Repository, https://github.com/ajyadav013/claude-kit

{claude_code_kit-0.32.0 → claude_code_kit-0.33.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "claude-code-kit"
-version = "0.32.0"
+version = "0.33.0"
 description = "Cookiecutter-style scaffolder for an autonomous Claude Code SDLC configuration (no app code, no Docker). Asks ordered questions and installs CLAUDE.md + .claude/ (rules, the chosen profile's agents/skills, hooks, artifact templates) + optional .mcp.json; run /sdlc to drive spec → review → build → test → security → ship through profile-aware quality gates, working memory, and a self-improving learnings loop."
 readme = "README.md"
 requires-python = ">=3.9"

{claude_code_kit-0.32.0 → claude_code_kit-0.33.0}/rules/mandatory-workflow.md

@@ -202,6 +202,30 @@ app entry points, shared barrels) require telling the user what and why, the imp
 getting approval first. NEVER add/remove/upgrade dependencies without confirmation.
 **Gate:** you understand every file/function you'll touch; the file list is task-scoped only.
 
+## 2a.5 — Reuse & YAGNI Gate `[Developer]`
+The cheapest code is the code you never write. Before adding a single new file, function, type, or
+abstraction, walk this ladder and **stop at the first rung that satisfies the need** — only what
+survives every rung gets written:
+
+1. **Does it need to exist at all?** If the task is satisfiable without this code, don't write it.
+2. **Already in the codebase?** Search first; reuse the existing utility, component, or pattern
+   rather than adding a parallel one.
+3. **Standard library?** Prefer the language's stdlib over a hand-rolled equivalent.
+4. **Native platform feature?** A built-in input type, a CSS feature, a DB constraint, a framework
+   primitive — use it before adding a dependency or custom code.
+5. **An existing dependency?** Reuse something already installed before pulling in a new one (and
+   adding a dependency needs user approval — see 2a).
+6. **The minimum that works?** No abstraction with a single caller, no config nobody sets, no layer
+   that only delegates, no flexibility no requirement asks for.
+
+Record any deliberate shortcut where you take it — `# shortcut: <ceiling> — <upgrade path>` (see
+`.claude/skills/simplification-debt/SKILL.md`) — so it is traceable, not silent debt.
+
+This is the **proactive twin** of the reactive `over-engineering-review` skill: the same
+delete/stdlib/native/yagni/shrink lenses, applied *before* the code exists rather than scanned out
+after. **Gate:** every new unit of code traces to a rung you could not satisfy more cheaply, and the
+implementation adds no abstraction the spec does not require.
+
 ## 2b — Write Implementation Code `[Developer]`
 Follow the approved spec + dev docs and your stack's rules.
 - Put files in the correct module/package; don't put module-specific code in shared dirs.
@@ -309,7 +333,7 @@ B1 understand → B2 failing test → B3 root cause → B4 fix → B5 quality ga
 Phase 1: 1a Understand [Orchestrator] → 1b Clarify → 1c Spec [Spec Writer]
   → 1d Dev docs [Dev Doc Writer] → 1e EM review [EM Reviewer, max 3]
   → 1e.5 Plan critique [Devil's Advocate, standard+] → 1f Story breakdown + coverage gate [Story Planner]
-Phase 2: 2a Read code [Developer] → 2b Implement → 2c Code review [Code Reviewer, max 5] → 2d Impact check
+Phase 2: 2a Read code [Developer] → 2a.5 Reuse/YAGNI gate → 2b Implement → 2c Code review [Code Reviewer, max 5] → 2d Impact check
 Phase 3: 3a Unit tests ─┐ 3b E2E tests ─┘ (parallel)
   → 3b.5 Test-coverage gate (blind review + Devil's Advocate)
   → 3b.6 Security (Security Clear) → 3b.7 DevOps + Observability (if applicable)
@@ -324,6 +348,7 @@ Phase 3: 3a Unit tests ─┐ 3b E2E tests ─┘ (parallel)
 | EM `APPROVED` (1e) | Plan critique (standard+) / Story Planner starts |
 | Plan critique CONFIRMED (1e.5, standard+) | Story breakdown is final |
 | Story coverage complete — every criterion mapped, no scope creep (1f) | Developer starts coding |
+| Reuse & YAGNI gate cleared (2a.5) | Writing implementation code (2b) |
 | Code Reviewer `APPROVED` (2c) | Testing starts |
 | Both testers pass (3a+3b) | Test-coverage gate |
 | Test-coverage PASS/CONFIRMED (3b.5) | Security review |

{claude_code_kit-0.32.0 → claude_code_kit-0.33.0}/skills/over-engineering-review/SKILL.md

@@ -18,6 +18,10 @@ description: Scans code for over-engineering ONLY and returns a terse delete-lis
   when you want the complexity axis alone, in a scannable form, with no other noise.
 - **Not `code-simplification`:** that skill *applies* the refactor and preserves behavior step by step.
   This skill produces the list; hand the list to `code-simplification` (or a developer) to execute.
+- **Proactive twin — `mandatory-workflow.md` §2a.5:** this skill scans complexity *out* after code
+  exists; the **Reuse & YAGNI Gate** (`.claude/rules/mandatory-workflow.md`, stage 2a.5) applies the
+  same five lenses *before* code is written. Run the gate to avoid the bloat; run this skill to catch
+  what slipped through.
 
 ## When to use
 

{claude_code_kit-0.32.0 → claude_code_kit-0.33.0}/src/claude_kit/__init__.py

@@ -7,4 +7,4 @@ Docker): ``claude-kit init`` asks ordered questions and lays down ``CLAUDE.md``
 as a plugin. Extensibility is data-driven via the ``catalog/`` (stacks, profiles, MCP).
 """
 
-__version__ = "0.32.0"
+__version__ = "0.33.0"