opencode-froggy 0.9.1 → 0.10.1

package/README.md

@@ -7,7 +7,7 @@
   <a href="https://www.npmjs.com/package/opencode-froggy"><img src="https://badge.fury.io/js/opencode-froggy.svg" alt="npm version"></a>
 </p>
 
-OpenCode plugin providing hooks, specialized agents (architect, doc-writer, rubber-duck, partner, code-reviewer, code-simplifier), skills (ask-questions-if-underspecified), and tools (gitingest, pdf-to-markdown, blockchain queries, agent-promote).
+OpenCode plugin providing hooks, specialized agents (architect, doc-writer, rubber-duck, partner, code-reviewer, code-simplifier), skills (ask-questions-if-underspecified, tdd), and tools (gitingest, pdf-to-markdown, blockchain queries, agent-promote).
 
 ---
 
@@ -134,6 +134,7 @@ Skills are contextual instructions loaded on demand via the `skill` tool. The ag
 | Skill | Description |
 |-------|-------------|
 | `ask-questions-if-underspecified` | Clarify requirements before implementing. Use when serious doubts arise. |
+| `tdd` | Apply Test-Driven Development workflow for new features and bugfixes. |
 
 #### Example: ask-questions-if-underspecified
 
@@ -164,6 +165,40 @@ After the user selects "JWT tokens", the agent confirms:
 
 Then implementation begins.
 
+#### Example: tdd
+
+**User request:**
+> "Add a function to calculate the total price with tax"
+
+**Agent response (after loading the skill):**
+
+The agent follows the TDD workflow:
+
+1. **Requirement Synthesis:**
+> "I'll create a function that calculates total price with tax. It should accept a price and tax rate, returning the total."
+
+2. **Test Specification:**
+```typescript
+describe("calculateTotalWithTax", () => {
+  it("should add tax to the base price", () => {
+    expect(calculateTotalWithTax(100, 0.2)).toBe(120)
+  })
+
+  it("should handle zero tax rate", () => {
+    expect(calculateTotalWithTax(100, 0)).toBe(100)
+  })
+})
+```
+
+3. **Implementation:**
+```typescript
+function calculateTotalWithTax(price: number, taxRate: number): number {
+  return price * (1 + taxRate)
+}
+```
+
+The tests are written first (red), then the minimal implementation to pass them (green).
+
 ### Discovery Locations
 
 Skills are discovered from the following locations, in order of increasing priority:

package/command/release.md

@@ -4,8 +4,7 @@ description: Prepare and execute a release with version bumping, changelog updat
 
 ## Context
 
-- Current version: !`node -p "require('./package.json').version"`
-- Latest tag: !`git describe --tags --abbrev=0 2>/dev/null || echo "none"`
+- Current version: !`git describe --tags --abbrev=0 2>/dev/null || echo "0.0.0"`
 - Commits since last tag: !`git log $(git describe --tags --abbrev=0 2>/dev/null || echo "HEAD~10")..HEAD --oneline 2>/dev/null || git log --oneline -10`
 
 ## CRITICAL CONSTRAINT
@@ -20,8 +19,8 @@ Any destructive or remote action requires confirmation, including:
 
 ### Step 1: Determine last released version
 
-1. Prefer the latest Git tag that matches `v<semver>`.
-2. If no matching tag exists, use the version in `package.json`.
+1. Use the latest Git tag that matches `v<semver>` or `<semver>`.
+2. If no tag exists, consider this the first release (`0.0.0`).
 3. Collect commits since the last version (tag to `HEAD`).
 
 ### Step 2: Propose version bump
@@ -35,10 +34,16 @@ Present the recommendation and ask the user to confirm before changing any files
 
 ### Step 3: Update release artifacts (after confirmation)
 
-- Update the version in `package.json`.
 - Update `CHANGELOG` with a new section for the version.
 - Summarize changes based on the commit range.
 - Preserve the existing changelog format.
+- Auto-detect and update the version file if present:
+  - Node.js: `package.json`
+  - Python: `pyproject.toml` or `setup.py`
+  - Rust: `Cargo.toml`
+  - PHP: `composer.json`
+  - Ruby: `*.gemspec`
+  - Go: tags only (no version file)
 
 ### Step 4: Tag and publish (after confirmation)
 

package/dist/index.js

@@ -198,7 +198,7 @@ const SmartfrogPlugin = async (ctx) => {
                 }
             }
             if (Object.keys(loadedAgents).length > 0) {
-                config.agent = { ...(config.agent ?? {}), ...loadedAgents };
+                config.agent = { ...loadedAgents, ...(config.agent ?? {}) };
             }
             if (Object.keys(commands).length > 0) {
                 config.command = { ...(config.command ?? {}), ...commands };

package/dist/tools/agent-promote.js

@@ -33,7 +33,15 @@ export function createAgentPromoteTool(client, pluginAgentNames) {
                     duration: 3000,
                 },
             });
-            await client.instance.dispose();
+            setTimeout(() => {
+                void client.instance.dispose().catch((error) => {
+                    log("[agent-promote] Delayed dispose failed", {
+                        name,
+                        grade,
+                        error: String(error),
+                    });
+                });
+            }, 0);
             return `Agent "${name}" changed to type "${grade}". Use Tab or <leader>a to select it.`;
         },
     });

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-froggy",
-  "version": "0.9.1",
+  "version": "0.10.1",
   "description": "OpenCode plugin with a hook layer (tool.before.*, session.idle...), agents (code-reviewer, doc-writer), and commands (/review-pr, /commit)",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -43,7 +43,7 @@
     "viem": "^2.44.1"
   },
   "devDependencies": {
-    "@opencode-ai/plugin": "latest",
+    "@opencode-ai/plugin": "^1.4.6",
     "@types/bun": "latest",
     "@types/js-yaml": "^4.0.9",
     "@vitest/coverage-v8": "^4.0.17",

package/skill/tdd/SKILL.md

@@ -0,0 +1,44 @@
+---
+name: tdd
+description: Apply Test-Driven Development workflow for new features and bugfixes.
+---
+
+# TDD Protocol
+
+## Core Principle
+
+- **TDD First**: Test-Driven Development is the default approach.
+- **Goal**: Prioritize behavioral correctness and regression safety over formal compliance.
+
+## Workflow
+
+1. **Requirement Synthesis**: Briefly summarize the requirements before coding.
+2. **Test Specification**: Write tests describing the expected behavior (unit, integration, or E2E).
+3. **Implementation**: Update the logic only to the extent required to satisfy those tests.
+
+## Mandatory Rules
+
+- **No Test, No Code**: Every new feature or bugfix must include relevant test coverage.
+- **Black-Box Testing**: Validate observable behavior, not internal implementation details.
+- **Merge Requirement**: Tests are mandatory for completion unless an explicit exception is documented.
+
+## Preferred Practice
+
+- **Red-Green-Refactor**: Start with a failing test whenever practical.
+- **Right-Sized Testing**:
+  - **Unit Tests**: For pure logic and isolated functions.
+  - **Integration Tests**: For system interactions and API boundaries.
+  - **E2E Tests**: For critical user journeys and "happy paths."
+
+## Explicit Exceptions (Must be justified)
+
+- Pure refactoring (where behavior remains identical).
+- Exploratory spikes or R&D.
+- UI/Styling iterations where unit tests offer diminishing returns.
+- Complex integrations where mocking is counterproductive.
+- Emergency hotfixes (requires a follow-up ticket for test debt).
+
+## Quality Bar
+
+- **Readability**: Tests must serve as documentation for the feature.
+- **Reliability**: Tests must be deterministic (no flakes) and decoupled from implementation internals.