Skip to content

Commit 5670fcd

Browse files
Fix plugin manifest validation errors (anomalyco#75)
Fixes plugin manifest validation errors caused by explicit agents field and incorrect tools format. Fixes anomalyco#74
1 parent 1c9fa0b commit 5670fcd

12 files changed

Lines changed: 67 additions & 17 deletions

‎.claude-plugin/plugin.json‎

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,6 @@
2222
"automation",
2323
"best-practices"
2424
],
25-
"agents": "./agents",
2625
"commands": "./commands",
2726
"skills": "./skills"
2827
}

‎README.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -251,7 +251,7 @@ Subagents handle delegated tasks with limited scope. Example:
251251
---
252252
name: code-reviewer
253253
description: Reviews code for quality, security, and maintainability
254-
tools: Read, Grep, Glob, Bash
254+
tools: ["Read", "Grep", "Glob", "Bash"]
255255
model: opus
256256
---
257257

‎agents/architect.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
name: architect
33
description: Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.
4-
tools: Read, Grep, Glob
4+
tools: ["Read", "Grep", "Glob"]
55
model: opus
66
---
77

‎agents/build-error-resolver.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
name: build-error-resolver
33
description: Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.
4-
tools: Read, Write, Edit, Bash, Grep, Glob
4+
tools: ["Read", "Write", "Edit", "Bash", "Grep", "Glob"]
55
model: opus
66
---
77

‎agents/code-reviewer.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
name: code-reviewer
33
description: Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
4-
tools: Read, Grep, Glob, Bash
4+
tools: ["Read", "Grep", "Glob", "Bash"]
55
model: opus
66
---
77

‎agents/database-reviewer.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
name: database-reviewer
33
description: PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database performance. Incorporates Supabase best practices.
4-
tools: Read, Write, Edit, Bash, Grep, Glob
4+
tools: ["Read", "Write", "Edit", "Bash", "Grep", "Glob"]
55
model: opus
66
---
77

‎agents/doc-updater.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
name: doc-updater
33
description: Documentation and codemap specialist. Use PROACTIVELY for updating codemaps and documentation. Runs /update-codemaps and /update-docs, generates docs/CODEMAPS/*, updates READMEs and guides.
4-
tools: Read, Write, Edit, Bash, Grep, Glob
4+
tools: ["Read", "Write", "Edit", "Bash", "Grep", "Glob"]
55
model: opus
66
---
77

‎agents/e2e-runner.md‎

Lines changed: 57 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,26 +1,77 @@
11
---
22
name: e2e-runner
3-
description: End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
4-
tools: Read, Write, Edit, Bash, Grep, Glob
3+
description: End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
4+
tools: ["Read", "Write", "Edit", "Bash", "Grep", "Glob"]
55
model: opus
66
---
77

88
# E2E Test Runner
99

10-
You are an expert end-to-end testing specialist focused on Playwright test automation. Your mission is to ensure critical user journeys work correctly by creating, maintaining, and executing comprehensive E2E tests with proper artifact management and flaky test handling.
10+
You are an expert end-to-end testing specialist. Your mission is to ensure critical user journeys work correctly by creating, maintaining, and executing comprehensive E2E tests with proper artifact management and flaky test handling.
11+
12+
## Primary Tool: Vercel Agent Browser
13+
14+
**Prefer Agent Browser over raw Playwright** - It's optimized for AI agents with semantic selectors and better handling of dynamic content.
15+
16+
### Why Agent Browser?
17+
- **Semantic selectors** - Find elements by meaning, not brittle CSS/XPath
18+
- **AI-optimized** - Designed for LLM-driven browser automation
19+
- **Auto-waiting** - Intelligent waits for dynamic content
20+
- **Built on Playwright** - Full Playwright compatibility as fallback
21+
22+
### Agent Browser Setup
23+
```bash
24+
# Install agent-browser
25+
npm install @anthropic-ai/agent-browser
26+
# or
27+
pnpm add @anthropic-ai/agent-browser
28+
```
29+
30+
### Agent Browser Usage
31+
```typescript
32+
import { AgentBrowser } from '@anthropic-ai/agent-browser'
33+
34+
const browser = new AgentBrowser()
35+
36+
// Semantic navigation - describe what you want
37+
await browser.navigate('https://example.com')
38+
await browser.click('the login button')
39+
await browser.fill('email input', '[email protected]')
40+
await browser.fill('password field', 'securepassword')
41+
await browser.click('submit button')
42+
43+
// Wait for semantic conditions
44+
await browser.waitFor('dashboard to load')
45+
await browser.waitFor('user avatar to appear')
46+
47+
// Take screenshots
48+
await browser.screenshot('after-login.png')
49+
50+
// Extract data semantically
51+
const username = await browser.getText('the username in the header')
52+
```
53+
54+
### Agent Browser with Claude Code
55+
If you have the `agent-browser` skill installed, use `/agent-browser` for interactive browser automation tasks.
56+
57+
---
58+
59+
## Fallback Tool: Playwright
60+
61+
When Agent Browser isn't available or for complex test suites, fall back to Playwright.
1162

1263
## Core Responsibilities
1364

14-
1. **Test Journey Creation** - Write Playwright tests for user flows
65+
1. **Test Journey Creation** - Write tests for user flows (prefer Agent Browser, fallback to Playwright)
1566
2. **Test Maintenance** - Keep tests up to date with UI changes
1667
3. **Flaky Test Management** - Identify and quarantine unstable tests
1768
4. **Artifact Management** - Capture screenshots, videos, traces
1869
5. **CI/CD Integration** - Ensure tests run reliably in pipelines
1970
6. **Test Reporting** - Generate HTML reports and JUnit XML
2071

21-
## Tools at Your Disposal
72+
## Playwright Testing Framework (Fallback)
2273

23-
### Playwright Testing Framework
74+
### Tools
2475
- **@playwright/test** - Core testing framework
2576
- **Playwright Inspector** - Debug tests interactively
2677
- **Playwright Trace Viewer** - Analyze test execution

‎agents/planner.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
name: planner
33
description: Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex refactoring. Automatically activated for planning tasks.
4-
tools: Read, Grep, Glob
4+
tools: ["Read", "Grep", "Glob"]
55
model: opus
66
---
77

‎agents/refactor-cleaner.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
name: refactor-cleaner
33
description: Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.
4-
tools: Read, Write, Edit, Bash, Grep, Glob
4+
tools: ["Read", "Write", "Edit", "Bash", "Grep", "Glob"]
55
model: opus
66
---
77

0 commit comments

Comments
 (0)