Multi-agent requirements/test-case analysis — contradiction detection, alignment validation, and cross-artifact reasoning
Route a natural language question to the appropriate analysis or answer it directly.
Show where a specific feature lives in the current codebase: which files implement it, how they communicate, and where each linked requirement appears in code. This is the same code-mapping output produced by `/bc:onboarding` between demo and assessment, but invokable on its own.
Analyze requirements and test cases to find contradictions, inconsistencies, and alignment gaps.
Find untested requirements, orphan test cases, and weak coverage between requirements and test cases.
Walk a new team member through the product feature-by-feature, pairing requirements with test cases. Each feature includes a guided demo, step-by-step confirmations, and an assessment with citations to requirement IDs. Progress is logged to a project-local file so the journey can be resumed across sessions.
You are the Buddy-Council Contradiction Agent. Your job is to detect contradictions, inconsistencies, and alignment gaps between requirements and test cases.
You are the Buddy-Council Coverage Agent. Your job is to identify coverage gaps between requirements and test cases — finding untested requirements, orphan test cases, and weak coverage.
You are the Buddy-Council Onboarding Agent. Your job is to walk a user through the product feature-by-feature, pairing requirements with test cases. You guide a paced demo, run an assessment, log progress to disk, and resume cleanly across sessions without losing the user's place.
You are the Buddy-Council Ticket Validation Agent. Your job is to validate a ticket description against existing requirements, resolve contradictions, fill gaps, generate a draft, and create a Jira ticket.
Analyze normalized requirements and test cases to identify coverage gaps, untested requirements, orphan test cases, and weak coverage.
Generate and grade a short assessment for one feature using its requirements and test cases. Cites requirement IDs in every answer. Adaptive remediation kicks in when the user gets multiple questions wrong. Records results to the progress log.
Group normalized requirements and test cases by feature and order them into a logical onboarding sequence. Reads optional feature_order from .buddy-council/sources.json. Produces the structure consumed by demo-feature and assess-feature.
Walk the user through one feature step by step with do/don't pairs from test cases, waiting for confirmation between steps. Honors interactive controls (next, back, skip, explain more, note, pause). Updates the progress log after every advance.
Analyze normalized requirements and test cases to find contradictions, inconsistencies, and missing alignment. Core analysis engine for the contradiction agent.
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A multi-agent plugin for detecting contradictions, coverage gaps, and alignment issues between requirements and test cases. Works with both Claude Code and Copilot CLI.
Data is fetched live from external systems via MCP — no RAG, no embeddings, no vector storage.
| Source | Type | Status |
|---|---|---|
| TestRail | Test cases | Supported (via MCP server) |
| Excel (Jama export) | Requirements | Supported (temporary Jama fallback) |
| Jama | Requirements | Planned (auth in progress) |
| Jira | Requirements | Planned |
| Jira | Ticket creation | Supported (via MCP server) |
| Qase | Test cases | Planned |
| Command | Description |
|---|---|
/bc:setup | Configure data sources and credentials |
/bc:contradiction | Detect contradictions between requirements and test cases |
/bc:coverage | Find untested requirements, orphan tests, and coverage gaps |
/bc:validate | Validate ticket description and create Jira ticket (with dry-run support) |
/bc:ask | Natural language query — routes to the right agent |
Step 1: Add the marketplace
/plugin marketplace add https://github.com/Omar-Hegazy-Integrant/buddy-council-plugin
Step 2: Install the plugin
/plugin install bc
Step 3: Reload
/reload-plugins
Step 1: Add the marketplace
copilot plugin marketplace add https://github.com/Omar-Hegazy-Integrant/buddy-council-plugin
Step 2: Install the plugin
copilot plugin install bc
Claude Code auto-approves the plugin's read-only operations via a bundled hook. Copilot CLI has no equivalent shippable hook, so pre-approve the plugin's read-only tools at launch with --allow-tool (curated — write operations like Jira ticket creation still prompt):
copilot --allow-tool='testrail(testrail_get_projects),testrail(testrail_get_suites),testrail(testrail_get_sections),testrail(testrail_get_cases),testrail(testrail_get_cases_by_refs),testrail(testrail_get_case),shell(jq:*),shell(gh api:*)'
Append the read-only tools for any other sources you configured:
jira(jira_get_projects),jira(jira_get_issue_types),jira(jira_get_issue)github(get_file_contents)The Excel parser (python3 … parse.py) and the TestRail connection test run once per analysis — when Copilot first prompts for them, choose "always allow" for the directory and it won't ask again. /bc:setup prints this recipe tailored to your configuration.
# Clone the repository
git clone https://github.com/Omar-Hegazy-Integrant/buddy-council-plugin.git
# Install the TestRail MCP server dependencies
cd buddy-council-plugin/mcp-servers/testrail-server
uv venv && uv pip install -e .
# Run with Claude Code
claude --plugin-dir /path/to/buddy-council-plugin
# Or with Copilot CLI
copilot plugin install /path/to/buddy-council-plugin
After installation, run the setup command to configure your data sources:
/bc:setup
This walks you through:
~/.buddy-council/secrets.json (never committed).mcp.json with TestRail credentials for the MCP serverAfter setup, restart your CLI tool or toggle the MCP server for it to take effect.
If you prefer to configure manually instead of using /bc:setup:
1. Create .buddy-council/sources.json (no secrets in this file):
{
"requirements": {
"provider": "excel",
"excel_path": "/absolute/path/to/requirements.xls"
},
"test_cases": {
"provider": "testrail",
"base_url": "https://your-instance.testrail.io",
"project_id": 1,
"suite_id": null
}
}
2. Create ~/.buddy-council/secrets.json:
{
"testrail": {
"username": "[email protected]",
"api_key": "your-testrail-api-key"
}
}
chmod 600 ~/.buddy-council/secrets.json
3. Create .mcp.json in the plugin root (copy from .mcp.example.json). It holds no secrets — only the non-secret base URL and BC_SECRETS_FILE, a pointer to the secrets file; the server reads credentials from ~/.buddy-council/secrets.json:
npx claudepluginhub omar-hegazy-integrant/buddy-council-plugin --plugin bc10 coordinated QA agents for Claude Code: chains diff analysis, AC compliance, test scenarios, browser validation, bug reports, and automation code generation.
QA skills for qa-toolkit domain.
Allure TestOps integration: test cases, launches, projects, defects, jobs, test plans
Verifiable AI-Augmented Engineering framework with traceable requirements, independent verification, and compliance-ready artifacts
Use this agent for analyzing test results, synthesizing test data, identifying trends, and generating quality metrics reports. This agent specializes in turning raw test data into actionable insights that drive quality improvements. Examples:\n\n<example>\nContext: Analyzing test suite results
Test planning and strategy methodologies for pre-code quality assurance. Includes test pyramid design, test case techniques, acceptance criteria, test data strategy, and automation ROI analysis.