Skip to content

v1.5.0: Mandatory Context Injection, Language Policy Enforcement & Procedural Workflow Enhancements

Choose a tag to compare

View all tags
@GulajavaMinistudio GulajavaMinistudio released this 14 Jul 05:00
v1.5.0
ea22c11

Release v1.5.0: Mandatory Context Injection, Language Policy Enforcement & Procedural Workflow Enhancements

This release focuses on enforcing rigorous context traceability through the Mandatory Context Injection Protocol, ensuring consistent language policy across all agent interactions, and refining procedural workflows for advanced agent skills.

🚀 Features & Enhancements

  • Mandatory Context Injection Protocol: Implemented strict context check protocols across all agents. Agents now require explicit attachment or mention of upstream documents (PRD, Spec, Plan) in the user's prompt before proceeding with analysis or generation. Added bypass options for minor, ad-hoc tasks.
  • Global Language Policy Override: Introduced a global translation override rule in AGENTS.md and updated SKILL.md files to mandate that all user-facing responses strictly comply with the project's language policy, preventing agents from breaking character or using hardcoded English responses.
  • Supplementary Skills Expansion: Added new supplementary skills including ponytail-lazy-senior-dev, memory-manager, and karpathy-guidelines to improve code reuse, context persistence, and adherence to AI coding best practices.

🛠️ Architecture & Under-the-Hood Fixes

  • Procedural Workflow Strictness: Enhanced the sequential development steps and updated skill execution guidelines (especially for @ClarificationAnalyst, @ArtifactConsistencyChecker, and @GodModeDev) to enforce mandatory procedural workflows and the usage of standardized report templates.
  • Context Protocol Refactoring: Refactored the context check protocols across multiple agent documents to ensure consistency in user prompts for required upstream documents. Removed redundant escape characters and improved phrasing for clarity.

📝 Documentation Updates

  • AGENTS.md: Overhauled communication guidelines, testing policies, and table formatting for mandatory upstream documents. Added reminders for saving progress before session changes.
  • README.md: Updated the table of contents, consolidated "Instructions" and "Prompts" into "Supplementary Skills", and added a section detailing dynamic persona activation for skill-driven agents.
  • Agent Skill Refinement: Mass refactoring of skill documentation (SKILL.md) for @PlannerArchitect, @GodModeDev, @ExpertCodeReviewer, and bug remediation templates for improved clarity, consistency, and alignment with AI-optimized standards.

Full Changelog: v1.4.0...v1.5.0

Assets 2
Loading