Reflective memory curation: pause → review → consolidate → release. Audits Claude memory + CLAUDE.md (+ serena if active), proposes dispositions via a read-only Opus curator agent, gates, and executes approved changes with archive-not-destroy safety.
Plugin meditate from marketplace foundry in piyushsatti/foundry. Commands read from the repo's manifest — 1 month ago.
applyExecute a human-approved memory-curation manifest against the live stores — promote/merge/keep/drop/promote-to-rule/demote-rule/generalize/specialize/deprecate/retire/link/amend/combine/split. Archives (never deletes); reports an optional-cleanup rm-block + CLAUDE.md additions/removals. Run manually
curateDispatch the meditate:curator Opus agent to sweep the memory store + CLAUDE.md (+ serena if active), then write the proposed-disposition manifest to a timestamped path for human review and /meditate:apply.
reviewRender a pending curate manifest readably — disposition table, destructive-op flags, the ⚠ CLAUDE.md-changes line, and the needs-human decisions. Read-only + re-runnable. Defaults to the latest manifest if no path is given. Run it between /meditate:curate and /meditate:apply.
curatorSole authority for promoting/curating agent memory across Claude memory + serena. Dispatch it to triage a worktree harvest (a .reap-manifest.md at worktree reap) OR to run a periodic store-wide curation sweep. It classifies each candidate by the 2-axis model (scope × genericity) + the routing test,
Orchestrate multi-agent plans with live dispatch telemetry. Bundles the progress-tracker MCP, the brief and subset scoping skills, and the full review capability (audit, hats, red-vs-blue + stance agents) composed from the shared library.
8 skills · 4 agents · 1 MCP server
Lens x stance review system: consult (partner), audit (neutral single reviewer), hats (blind panel), and red-vs-blue (attack/verify pair) on a shared hat wardrobe.
5 skills · 4 agents · hooks
KAOS project compass: a DB-canonical spec substrate with an MCP server exposing read/write tools over a project's goal graph.
2 skills · 1 MCP server
Dev-environment tooling: worktree-native lifecycle (add/check/archive/revive/reap) with memory wiring.
1 skill
A deliberate, state-aware compaction boundary: warns as occupancy rises toward the measured trigger, and at every boundary writes a handoff per live thread plus a reference map the next session is pointed at.
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Design fluency for frontend development. 1 skill with 24 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
1 skill · 4 agents · hooks
AgentDB (external: maintained in ruvnet/agentdb, pinned to commit 27678c3, plugin 3.6.0): agentdb's own standalone MCP server pinned to [email protected] (vector memory with get/list/update/delete for records, patterns and skills, hybrid keyword + vector episode search and an opt-in local cross-encoder, an opt-in aidefence injection guard on memory writes, reflexion, skills, outcome feedback, capabilities report), a memory-specialist agent, 3 skills, /agentdb-status, and the agentdb mod guard that keeps secrets out of memory and refuses delete/reset unless allowed. Complements ruflo-agentdb, which reaches AgentDB through ruflo's server
3 skills · 1 command · 1 agent · 1 MCP server
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents
7 skills · 7 commands · 2 agents · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.