Optimize agent files and add developer tooling (VS Code tasks, build/lint scripts)

[Copilot]

Pull Request

Description

Reduces agent file token consumption by 69% (662→203 lines) while preserving essential instructions. Adds developer tooling following SarifMark patterns for improved workflow: VS Code tasks and cross-platform build/lint scripts.

Changes

• Agent file optimization: Converted verbose documentation to Quick Reference format

  • AGENTS.md: 213→64 lines (70% reduction)
  • .github/agents/documentation-writer.md: 112→47 lines (58% reduction)
  • .github/agents/project-maintainer.md: 201→54 lines (73% reduction)
  • .github/agents/software-quality-enforcer.md: 136→38 lines (72% reduction)
  • Added agent invocation guidance for task routing

• VS Code tasks (.vscode/tasks.json): Standard tasks for build, test, format, lint (markdown/spell/YAML), coverage, requirements verification

• Cross-platform scripts: Build and lint scripts for command-line usage

  • build.bat / build.sh: Build and test scripts for Windows and Unix
  • lint.bat / lint.sh: Run all linters (markdown, spell check, YAML, code formatting)

• Dependency update: SarifMark 1.0.1→1.1.0

Type of Change

• Code quality improvement
• Documentation update

Pre-Submission Checklist

Build and Test

• Code builds successfully: dotnet build --configuration Release
• All tests pass: dotnet test --configuration Release
• Code produces zero warnings

Code Quality

• Code formatting is correct: dotnet format --verify-no-changes
• New code has appropriate XML documentation comments
• Static analyzer warnings have been addressed

Quality Checks

Please run the following checks before submitting:

• Spell checker passes: cspell "**/*.{md,cs}"
• Markdown linter passes: markdownlint "**/*.md"
• YAML linter passes: yamllint '**/*.{yml,yaml}'

Testing

• Added unit tests for new functionality
• Updated existing tests if behavior changed
• All tests follow the AAA (Arrange, Act, Assert) pattern
• Test coverage is maintained or improved

Documentation

• Updated README.md (if applicable)
• Updated ARCHITECTURE.md (if applicable)
• Added code examples for new features (if applicable)
• Updated requirements.yaml (if applicable)

Additional Notes

Token efficiency improvements enable more context in agent conversations while maintaining instruction quality. VS Code tasks and command-line scripts standardize common operations across team, supporting both IDE and terminal-based workflows on Windows and Unix systems.

Original prompt

Please review the general project structure and all files looking for appropriate improvements and updates. Consider running specialzied agents to review specific tasks such as code quality and technical documentation. Additionally the agent files (AGENTS.md and the .github/agents/xxx.md) files should be optimized to lower the token counts while still preserving appropriate instructions - possibly also including directions to use specific agents for specific tasks.

Note that this was recently done on https://github.com/demaconsulting/SarifMark and yielded good results that may be worth inspecting:

• .vscode/tasks.json to better define common tasks

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[Malcolmnixon]

@copilot Other interesting improvements on the https://github.com/demaconsulting/SarifMark projects include:

• build.bat and build.sh scripts
• lint.bat and lint.sh scripts

[Copilot]

@copilot Other interesting improvements on the https://github.com/demaconsulting/SarifMark projects include:

• build.bat and build.sh scripts
• lint.bat and lint.sh scripts
  ...

Added build and lint scripts following the SarifMark pattern in commit 8b12075. The scripts provide convenient cross-platform command-line interfaces for building/testing and running all linters (markdown, spell check, YAML, and code formatting).