Stats
Actions
Tags
From agent-teams-coder
Use when team agents need to read, write, or manage shared team knowledge (architecture decisions, API conventions, coding standards). Provides the approval-based governance model for shared memory.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-teams-coder:shared-memory-protocolThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The shared memory system ensures team knowledge consistency through an approval-based governance model.
The shared memory system ensures team knowledge consistency through an approval-based governance model.
shared-memory.json ← Protected team knowledge store
approval-queue.json ← Pending change requests
status.json ← Real-time team state (open access)
| Operation | Who | Method |
|---|---|---|
| Read shared-memory | All agents | Direct file read |
| Write shared-memory | Non-leader agents | Submit request → Leader approves |
| Write shared-memory | Marshall (Leader) | Direct write |
| Read/Write status | All agents | Direct access |
npx claudepluginhub xinjing-guo/agent-teams-coder --plugin agent-teams-coder3-tier markdown memory protocol (shared/agent/conversation) for cross-session knowledge accumulation. Automatically injects relevant memory into agent context at task start.
Saves architectural decisions, patterns, conventions, or project knowledge to personal or team Cognis persistent memory using node scripts.
Captures team knowledge at session end by reviewing changes, classifying insights, checking for conflicts, and proposing governed memories via teamkb MCP tools. Use when wrapping up with team-relevant discoveries or importing docs into the brain.