fix(build): add missing subagents and shared instructions to collection manifests

[WilliamBerryiii]

Collection manifests had gaps where parent agents declared subagent dependencies that were not listed in the corresponding collections/*.collection.yml files. The project-planning collection was missing five RPI subagent entries, the design-thinking and experimental collections were missing the shared hve-core-location instruction, and the project-planning.collection.md description was incomplete. This PR closed all identified gaps and regenerated affected plugin outputs.

Description

Collection YAML Manifest Completeness

Five kind: agent entries were added to project-planning.collection.yml for researcher-subagent, plan-validator, phase-implementor, rpi-validator, and implementation-validator, all referencing canonical files in .github/agents/hve-core/subagents/. A kind: instruction entry for hve-core-location.instructions.md was added to both design-thinking.collection.yml and experimental.collection.yml.

Collection Markdown Description

project-planning.collection.md was expanded with four previously missing agent descriptions (Product Manager Advisor, UX/UI Designer, System Architecture Reviewer, and RPI Agent) and a new "Supporting subagents included" section with five subagent descriptions. Entries were reordered for logical grouping, and all bullets were normalized to the - **Name** — convention matching other collection markdown files.

Plugin Output Regeneration

All affected plugin outputs were regenerated via npm run plugin:generate. Three README files gained new table rows (plugins/design-thinking/README.md, plugins/experimental/README.md, plugins/project-planning/README.md), and seven new symlinks were created under plugins/ directories pointing to canonical source files.

Related Issue(s)

Fixes #802

Type of Change

Select all that apply:

Code & Documentation:

• Bug fix (non-breaking change fixing an issue)
• New feature (non-breaking change adding functionality)
• Breaking change (fix or feature causing existing functionality to change)
• Documentation update

Infrastructure & Configuration:

• GitHub Actions workflow
• Linting configuration (markdown, PowerShell, etc.)
• Security configuration
• DevContainer configuration
• Dependency update

AI Artifacts:

• Reviewed contribution with prompt-builder agent and addressed all feedback
• Copilot instructions (.github/instructions/*.instructions.md)
• Copilot prompt (.github/prompts/*.prompt.md)
• Copilot agent (.github/agents/*.agent.md)
• Copilot skill (.github/skills/*/SKILL.md)

Note for AI Artifact Contributors:

• Agents: Research, indexing/referencing other project (using standard VS Code GitHub Copilot/MCP tools), planning, and general implementation agents likely already exist. Review .github/agents/ before creating new ones.
• Skills: Must include both bash and PowerShell scripts. See Skills.
• Model Versions: Only contributions targeting the latest Anthropic and OpenAI models will be accepted. Older model versions (e.g., GPT-3.5, Claude 3) will be rejected.
• See Agents Not Accepted and Model Version Requirements.

Other:

• Script/automation (.ps1, .sh, .py)
• Other (please describe):

Sample Prompts (for AI Artifact Contributions)

User Request:

Execution Flow:

Output Artifacts:

Success Indicators:

For detailed contribution requirements, see:

• Common Standards: docs/contributing/ai-artifacts-common.md - Shared standards for XML blocks, markdown quality, RFC 2119, validation, and testing
• Agents: docs/contributing/custom-agents.md - Agent configurations with tools and behavior patterns
• Prompts: docs/contributing/prompts.md - Workflow-specific guidance with template variables
• Instructions: docs/contributing/instructions.md - Technology-specific standards with glob patterns
• Skills: docs/contributing/skills.md - Task execution utilities with cross-platform scripts

Testing

Automated validation performed during PR generation:

• Markdown linting (npm run lint:md): Passed (0 errors, 283 files)
• Spell checking (npm run spell-check): Passed (0 issues, 198 files)
• Frontmatter validation (npm run lint:frontmatter): Passed (0 errors, 0 warnings)
• Skill structure validation (npm run validate:skills): Passed (2 skills, 0 errors)
• Link validation (npm run lint:md-links): Passed
• PowerShell analysis (npm run lint:ps): Passed (all files clean)
• Plugin freshness (npm run plugin:generate): Passed (idempotent, no diff)

Security analysis found no sensitive data exposure, dependency vulnerabilities, or privilege modifications. Conventional commits compliance verified. No unintended file changes detected.

Manual testing was not performed.

Checklist

Required Checks

• Documentation is updated (if applicable)
• Files follow existing naming conventions
• Changes are backwards compatible (if applicable)
• Tests added for new functionality (if applicable) (N/A — no new testable functionality)

AI Artifact Contributions

• Used /prompt-analyze to review contribution
• Addressed all feedback from prompt-builder review
• Verified contribution follows common standards and type-specific requirements

Required Automated Checks

The following validation commands must pass before merging:

• Markdown linting: npm run lint:md
• Spell checking: npm run spell-check
• Frontmatter validation: npm run lint:frontmatter
• Skill structure validation: npm run validate:skills
• Link validation: npm run lint:md-links
• PowerShell analysis: npm run lint:ps
• Plugin freshness: npm run plugin:generate

Security Considerations

• This PR does not contain any sensitive or NDA information
• Any new dependencies have been reviewed for security issues (N/A — no dependency changes)
• Security-related scripts follow the principle of least privilege (N/A — no security script changes)

Additional Notes

All 14 changed files were verified: 4 source files modified, 7 symlinks added, 3 plugin READMEs regenerated. Plugin output freshness was confirmed via idempotent npm run plugin:generate re-run during implementation.

[github-actions]

Dependency Review

✅ No vulnerabilities or license issues or OpenSSF Scorecard issues found.

Scanned Files

None