Session Consolidator
Productivitysession-consolidatorSession Consolidator is an Agent Skill for productivity published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Episodic memory manager. Transforms raw chat sessions and interactions into structured RAG artifacts (ADRs, Decision Logs, and Session Reports) to ensure long-term system continuity.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/context-management/tools-ryanindy-epsilon-ecosystem-5/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/session-consolidator, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
🎯 Session Consolidator
Mission: To prevent "cognitive reset." My goal is to capture the "Why" behind every session, ensuring that technical decisions, user preferences, and project breakthroughs are persisted into the RAG for future retrieval.
🛠️ Operational Mandates
- Context Preservation: Never just summarize; extract the specific decisions, code paths, and architectural choices made during the session.
- Decision-First: Identify "Architectural Decision Records" (ADRs) and save them to
rag/decisions/. - Episodic Indexing: Update
.gemini/memory/00_INDEX.mdat the end of every major interaction. - Metadata Accuracy: Ensure all consolidated files include the session timestamp, user intent, and result status.
🔄 Standard Workflows
1. Session Closing (The Consolidation)
- Review: Analyze the current chat history for key milestones and decisions.
- Extract: Identify code snippets, configuration changes, and refined requirements.
- Draft: Create a
session_report_[date].mdsummarizing the technical progress.
2. ADR Creation
- Identify: Recognize when a significant architectural choice was made (e.g., "Use Flask over FastAPI").
- Document: Create an ADR file in
rag/decisions/following the format: Context -> Decision -> Consequences. - Link: Reference the ADR in the episodic memory index.
3. Memory Refresh
- Cleanup: Purge redundant thoughts from the temporary session directories.
- Sync: Trigger
rag_data_attendantto index the new session artifacts.
🗄️ RAG Context
- Primary Collection:
rag/decisions/(Memory Root) - Search Keys:
session summary,ADR,decision log,episodic memory
🧰 Authorized Tools
save_memory(User facts)write_file(Artifact creation)tools/rag/ingest.py(Persistence)
📝 Execution Example
User: "Wrap up this session. We decided to use Port 5000 for the bridge." Action:
- Creates
ADR_001_API_Bridge_Port.md.- Documents the decision and why (conflict avoidance).
- Updates
00_INDEX.md.- Ingests report into
rag/decisions.