agent-memorylisted

3-tier markdown memory protocol (shared/agent/conversation) for cross-session knowledge. TRIGGER when: reading or writing agent memory files, choosing which memory tier an insight belongs in, or starting a task needing prior context. SKIP: vector recall (use semantic-memory-mcp); distilling conversations into candidates (use distill).
komluk/scaffolding · ★ 1 · AI & Automation · score 74

Install: claude install-skill komluk/scaffolding

# Agent Memory Protocol 3-tier persistent memory system for cross-session knowledge accumulation. ## Memory Tiers | Tier | Path | Scope | Written By | Read By | |------|------|-------|------------|---------| | **Shared** | `.scaffolding/agent-memory/shared/KNOWLEDGE.md` | Whole project | Any agent | All agents | | **Agent** | `.scaffolding/agent-memory/agents/{agent-name}/MEMORY.md` | Per agent | Owning agent | Own agent + architect | | **Conversation** | `.scaffolding/conversations/{conversation_id}/agent-memory/context.md` | Per conversation | Any agent in conversation | Agents in same conversation | ## Automatic Injection Memory is auto-injected into agent context via `recall_for_agent()` in the task execution pipeline. When a task starts, the system reads: 1. `.scaffolding/agent-memory/shared/KNOWLEDGE.md` (always) 2. `.scaffolding/agent-memory/agents/{agent-name}/MEMORY.md` (when agent_name is known) 3. `.scaffolding/conversations/{id}/agent-memory/context.md` (when conversation_id is provided) This means agents receive memory context automatically. Manual reading on first turn is optional but recommended for verifying latest data. ## On First Turn Before starting work, optionally read available memory for latest content (skip if files don't exist): 1. Read `.scaffolding/agent-memory/shared/KNOWLEDGE.md` 2. Read `.scaffolding/agent-memory/agents/{your-agent-name}/MEMORY.md` 3. If `conversation_id` is provided in task context: Read `.scaffolding/conversations/{co