@simplysm/claude 13.0.24 → 13.0.25

package/claude/agents/sd-api-reviewer.md

@@ -1,7 +1,7 @@
 ---
 name: sd-api-reviewer
 description: Reviews a library's public API for developer experience (DX) quality - naming consistency, industry standard alignment, intuitiveness, error messages, type hints, configuration complexity, and usage pattern coherence
-model: inherit
+model: opus
 ---
 
 You are an expert API/DX reviewer who evaluates libraries from the **consumer's perspective**. Your goal is to identify friction points that developers encounter when using a package.

package/claude/agents/sd-code-reviewer.md

@@ -1,7 +1,7 @@
 ---
 name: sd-code-reviewer
 description: Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter
-model: inherit
+model: opus
 ---
 
 You are an expert code reviewer specializing in modern software development across multiple languages and frameworks. Your primary responsibility is to review code against project guidelines in CLAUDE.md with high precision to minimize false positives.

package/claude/agents/sd-code-simplifier.md

@@ -1,7 +1,7 @@
 ---
 name: sd-code-simplifier
 description: Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
-model: inherit
+model: opus
 ---
 
 You are an expert code simplification specialist focused on enhancing code clarity, consistency, and maintainability while preserving exact functionality. Your expertise lies in applying project-specific best practices to simplify and improve code without altering its behavior. You prioritize readable, explicit code over overly compact solutions. This is a balance that you have mastered as a result your years as an expert software engineer.

package/claude/agents/sd-security-reviewer.md

@@ -1,7 +1,7 @@
 ---
 name: sd-security-reviewer
 description: Reviews ORM queries and service endpoints for SQL injection and input validation vulnerabilities in simplysm's string-escaping ORM
-model: inherit
+model: opus
 ---
 
 You are a security-focused code reviewer for the simplysm framework.

package/claude/skills/sd-brainstorm/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: sd-brainstorm
 description: "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation."
-model: inherit
+model: opus
 ---
 
 # Brainstorming Ideas Into Designs

package/claude/skills/sd-check/SKILL.md

@@ -2,7 +2,7 @@
 name: sd-check
 description: Verify code via typecheck, lint, and tests
 argument-hint: "[path]"
-model: sonnet
+model: opus
 ---
 
 ## Usage
@@ -59,43 +59,85 @@ If all pre-checks pass, report "Environment OK" and proceed to code verification
 
 ## Code Verification
 
-Run the following 3 checks **in order**.
-If errors occur at any step, **fix the code directly** and re-run that step.
-Repeat until no errors remain, then proceed to the next step.
+Run verification checks using haiku agents for command execution, then analyze and fix errors.
+Repeat until all checks pass.
 
-### Step 1: TypeScript Typecheck
+### Step 1: Launch Verification Agents (Parallel)
 
+Launch 3 haiku agents in parallel using the Task tool.
+
+**Important**: Replace `[path]` in the commands below with the actual path argument provided by the user. If no argument was provided, omit the path (runs on entire project).
+
+**Agent 1 - Typecheck:**
 ```
-pnpm typecheck $ARGUMENTS
+Task tool with:
+  subagent_type: Bash
+  model: haiku
+  description: "Run typecheck"
+  prompt: "Run `pnpm typecheck [path]` and return the full output. Do NOT analyze or fix errors - just report the raw output."
 ```
 
-On error: Read the failing file to identify the cause, fix with Edit, then re-run typecheck.
-
-### Step 2: ESLint Lint
+**Agent 2 - Lint:**
+```
+Task tool with:
+  subagent_type: Bash
+  model: haiku
+  description: "Run lint with auto-fix"
+  prompt: "Run `pnpm lint --fix [path]` and return the full output. Do NOT analyze or fix errors - just report the raw output."
+```
 
+**Agent 3 - Test:**
 ```
-pnpm lint --fix $ARGUMENTS
+Task tool with:
+  subagent_type: Bash
+  model: haiku
+  description: "Run tests"
+  prompt: "Run `pnpm vitest [path] --run` and return the full output. Do NOT analyze or fix errors - just report the raw output."
 ```
 
-On error: Read the failing file, fix with Edit, then re-run lint.
+### Step 2: Collect Results and Fix Errors
 
-### Step 3: Tests (Vitest)
+Wait for all 3 agents to complete. Collect their outputs.
 
-```
-pnpm vitest $ARGUMENTS --run
-```
+If any errors are found:
+
+1. **Analyze errors by priority**: typecheck → lint → test
+   - Typecheck errors may cause lint/test errors, so fix them first
+2. **Read failing files** to identify root causes
+3. **Fix with Edit**:
+   - Typecheck errors: Fix type issues
+   - Lint errors: Fix linting issues (most should be auto-fixed by `--fix`)
+   - Test failures:
+     - Run `git diff` to check for intentional code changes
+     - If intentional changes not reflected in tests: Update test code
+     - If source code bug: Fix source code
+4. Proceed to Step 3
+
+If all checks passed: Proceed to Completion.
+
+### Step 3: Re-verify (Loop)
+
+Go back to Step 1 and launch the 3 haiku agents again.
+Repeat until all checks pass with no errors.
+
+## Common Mistakes
+
+### Running checks sequentially instead of parallel
+❌ **Wrong**: Launch agent 1, wait, then agent 2, wait, then agent 3
+✅ **Right**: Launch all 3 agents in a single message with multiple Task tool calls
 
-Run with `--run` flag for single execution (no watch mode).
-Some packages may require integration tests as configured in vitest.config.ts.
+### Fixing before collecting all results
+❌ **Wrong**: Agent 1 returns error → fix immediately → launch agents again
+✅ **Right**: Wait for all 3 agents → collect all errors → fix in priority order → re-verify
 
-On failure:
+### Skipping re-verification after fixes
+❌ **Wrong**: Fix typecheck error → assume lint/test still pass
+✅ **Right**: Always re-run all 3 checks after any fix (fixes can introduce new errors)
 
-1. **Check git diff**: Run `git diff` (staged + unstaged) to identify intentional code changes.
-2. **Determine root cause**: Check whether the test failure is caused by intentional code changes (feature changes, API changes, behavior changes) that haven't been reflected in tests yet.
-   - **Intentional changes not reflected in tests**: Update the **test code** to match the new behavior, not the source code.
-   - **Source code bug**: Fix the source code.
-3. Re-run tests after the fix.
+### Using wrong model for agents
+❌ **Wrong**: `model: opus` or `model: sonnet` for verification agents
+✅ **Right**: `model: haiku` for command execution (cheaper, faster)
 
 ## Completion Criteria
 
-Complete when all 3 steps pass without errors.
+Complete when all 3 checks pass without errors.

package/claude/skills/sd-plan/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: sd-plan
 description: Use when you have a spec or requirements for a multi-step task, before touching code
-model: inherit
+model: opus
 ---
 
 # Writing Plans

package/claude/skills/sd-tdd/SKILL.md

@@ -2,7 +2,7 @@
 name: sd-tdd
 description: Use when implementing any feature or bugfix, before writing implementation code
 user-invocable: false
-model: inherit
+model: opus
 ---
 
 # Test-Driven Development (TDD)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@simplysm/claude",
-  "version": "13.0.24",
+  "version": "13.0.25",
   "description": "Simplysm Claude Code skills/agents — auto-installs via postinstall",
   "author": "김석래",
   "license": "Apache-2.0",