From memfleet-skills
Use to read current coordination state for a symbol — recent episodes, active intents, dominant intent, conflict density, Y-doc thread. Triggered by: 'is anyone working on X', pre-edit reconnaissance, checking fleet activity on a symbol, reading another agent's recent work.
How this skill is triggered — by the user, by Claude, or both
Slash command
/memfleet-skills:memfleet-node-stateThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Before touching an unfamiliar symbol, read its `NodeState` rollup. In one call you get:
Before touching an unfamiliar symbol, read its NodeState rollup. In one call you get:
This is the query that replaces "read 500 lines of prose from other agents".
get_node_state(repo_id, symbol, last_n?) — rollup + top episodes (O(1))ydoc_read(repo_id, symbol) — full thread + current NodeState blob1. get_node_state on the symbol you are about to touch
2. If dominant_intent is a Refactor(RenameSymbol) in-flight → wait or replan
3. If conflict_density is high → assume collision, publish_intent with shorter TTL
4. If recent episodes include your Exploratory intent → you already probed here
get_node_state is synchronous and O(1) — the rollup is precomputed by record_episode. Do not worry about calling it on hot paths.
npx claudepluginhub syncable-dev/memfleet-public --plugin memfleet-skillsReconstructs AI agent session history to summarize project state, decisions, and workstreams when onboarding to a brownfield repo. Recommends gates from open decisions.
Coordinates with other AI agents using Wit CLI before code edits: declares intents, locks symbols, checks conflicts to prevent merge issues in multi-agent workflows.
Guides efficient use of context-mem MCP tools: compress large outputs, search before re-reading files, persist knowledge across sessions, and manage token budget.