Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Query AgentDB through the controller bridge -- semantic routing, hierarchical recall, causal graphs, context synthesis, pattern store/search
.claude/skills/ruvnet-agentdb-query/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 156% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 50% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 234% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -5% | 0% |
Query and manage AgentDB through the controller bridge. AgentDB exposes 15 agentdb_* MCP tools; this skill enumerates the standard usage path.
When you need to store, retrieve, or search knowledge across agent sessions. AgentDB provides hierarchical storage, causal knowledge graphs, semantic routing, and context synthesis.
mcp__plugin_ruflo-core_ruflo__agentdb_health. Sanity-check available: true.mcp__plugin_ruflo-core_ruflo__agentdb_session-start if not already active.mcp__plugin_ruflo-core_ruflo__agentdb_hierarchical-store for structured tier-keyed data (tiers: working|episodic|semantic).mcp__plugin_ruflo-core_ruflo__agentdb_hierarchical-recall with a query.mcp__plugin_ruflo-core_ruflo__agentdb_pattern-search for learned patterns (ReasoningBank-routed).mcp__plugin_ruflo-core_ruflo__agentdb_context-synthesize to combine multiple memories.mcp__plugin_ruflo-core_ruflo__agentdb_causal-edge to link related knowledge.Call mcp__plugin_ruflo-core_ruflo__agentdb_controllers to list the runtime registry. Functional categories surfaced via the 15 MCP tools:
agentdb_hierarchical-store, _recall (tier-routed)agentdb_pattern-store, _search (ReasoningBank-routed)agentdb_semantic-route, _context-synthesizeagentdb_causal-edge (graph-node backend with bridge fallback)agentdb_health, _controllers, _session-start, _session-endagentdb_batch (≤500 entries), _consolidateagentdb_feedbackNamespace strings apply to memory_* and embeddings_search only. The agentdb_hierarchical-*, agentdb_pattern-*, and agentdb_causal-edge tools route by tier or controller, not namespace. Don't pass namespace: 'foo' to those tools — it will be silently ignored. See plugin README "Namespace convention".
controller: 'memory-store-fallback' — pattern persisted via memory_store --namespace pattern. NOT a failure._graphNodeBackend: true — causal-edge handled by @ruvector/graph-node.success: false, error: '...Use memory_store/memory_search instead.' — bridge unavailable; switch to memory_* tools per the README replacement table.bashnpx @claude-flow/cli@latest memory search --query "your query" --namespace patterns npx @claude-flow/cli@latest memory store --key "key" --value "value" --namespace patterns npx @claude-flow/cli@latest memory list --namespace patterns
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→fail | 4,685 | 9,170 | +96% | 1 | 1 | 0% | 307 | 1,961 | +539% | 0 | 0 | — |
case-05 | fail→pass | 3,087 | 4,852 | +57% | 1 | 1 | 0% | 682 | 1,745 | +156% | 0 | 0 | — |
case-01 | fail→fail | 3,917 | 2,995 | -24% | 1 | 1 | 0% | 755 | 1,122 | +49% | 0 | 0 | — |
case-02 | fail→fail | 13,379 | 5,353 | -60% | 1 | 1 | 0% | 2,452 | 1,203 | -51% | 0 | 0 | — |
case-03 | fail→fail | 14,358 | 3,705 | -74% | 1 | 1 | 0% | 2,210 | 858 | -61% | 0 | 0 | — |
case-04 | fail→pass | 6,707 | 5,609 | -16% | 1 | 1 | 0% | 1,356 | 2,035 | +50% | 0 | 0 | — |
case-07 | pass→pass | 8,866 | 2,698 | -70% | 1 | 1 | 0% | 1,786 | 1,257 | -30% | 0 | 0 | — |
case-08 | fail→pass | 2,858 | 3,612 | +26% | 1 | 1 | 0% | 458 | 1,528 | +234% | 0 | 0 | — |
case-09 | fail→pass | 9,402 | 2,826 | -70% | 1 | 1 | 0% | 1,821 | 1,405 | -23% | 0 | 0 | — |
case-10 | pass→pass | 8,320 | 2,223 | -73% | 1 | 1 | 0% | 1,594 | 1,204 | -24% | 0 | 0 | — |
case-11 | pass→pass | 9,409 | 3,532 | -62% | 1 | 1 | 0% | 1,686 | 1,424 | -16% | 0 | 0 | — |
case-12 | pass→pass | 7,125 | 3,616 | -49% | 1 | 1 | 0% | 1,359 | 1,647 | +21% | 0 | 0 | — |
case-13 | pass→pass | 11,216 | 4,756 | -58% | 1 | 1 | 0% | 2,077 | 1,829 | -12% | 0 | 0 | — |
case-14 | fail→pass | 7,046 | 2,361 | -66% | 1 | 1 | 0% | 1,344 | 1,273 | -5% | 0 | 0 | — |
case-15 | fail→pass | 9,005 | 3,530 | -61% | 1 | 1 | 0% | 1,667 | 1,487 | -11% | 0 | 0 | — |
case-16 | fail→pass | 9,935 | 2,368 | -76% | 1 | 1 | 0% | 2,130 | 1,313 | -38% | 0 | 0 | — |
case-17 | fail→pass | 5,177 | 1,607 | -69% | 1 | 1 | 0% | 1,083 | 1,146 | +6% | 0 | 0 | — |
case-18 | fail→pass | 7,266 | 2,018 | -72% | 1 | 1 | 0% | 1,302 | 1,181 | -9% | 0 | 0 | — |
case-19 | fail→pass | 4,601 | 1,626 | -65% | 1 | 1 | 0% | 879 | 1,140 | +30% | 0 | 0 | — |
case-20 | pass→pass | 3,313 | 3,248 | -2% | 1 | 1 | 0% | 639 | 1,460 | +128% | 0 | 0 | — |
case-21 | pass→pass | 11,305 | 14,177 | +25% | 1 | 1 | 0% | 2,488 | 3,493 | +40% | 0 | 0 | — |
case-22 | pass→pass | 2,390 | 2,641 | +11% | 1 | 1 | 0% | 360 | 1,315 | +265% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 18 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +45 percentage points is the difference between those two pass rates over the 18 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.