Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From agentdb-causal
Traces AgentDB's causal graph backwards from a memory, test, or ADR to surface the decision chain that produced it. Renders the chain as a tree, capping at 15 nodes, and flags low-confidence edges.
How this command is triggered — by the user, by Claude, or both
Slash command
/agentdb-causal:explain-linkThe summary Claude sees in its command listing — used to decide when to auto-load this command
Use the `agentdb-causal-explain` skill to walk the causal graph backwards from the user's target. If the user names the target after `/explain-link` (a test name, an episode id, an ADR), use it. Otherwise pick the most recent failure / regression / decision in the conversation. Render the result as a tree (or path if linear) with relations on the edges. Keep `maxDepth` at 3 unless the user asks for deeper. Cap output at 15 nodes. If the chain has gaps (low-confidence edges), surface them explicitly — "we have evidence A→B and C→D but the link B→C is missing or weak (confidence 0.31)" — r...
Use the agentdb-causal-explain skill to walk the causal graph backwards from the user's target.
If the user names the target after /explain-link (a test name, an episode id, an ADR), use it. Otherwise pick the most recent failure / regression / decision in the conversation.
Render the result as a tree (or path if linear) with relations on the edges. Keep maxDepth at 3 unless the user asks for deeper. Cap output at 15 nodes.
If the chain has gaps (low-confidence edges), surface them explicitly — "we have evidence A→B and C→D but the link B→C is missing or weak (confidence 0.31)" — rather than papering over them.
3plugins reuse this command
First indexed May 6, 2026
npx claudepluginhub oliverv/agentdb --plugin agentdb-causal/explain-linkTraces AgentDB's causal graph backwards from a memory, test, or ADR to surface the decision chain that produced it. Renders the chain as a tree, capping at 15 nodes, and flags low-confidence edges.
/graphDisplays related memories as an indented knowledge-graph tree up to 3 hops from a given ID or prefix, showing relationship types and directions (e.g., → supersedes, ← derived_from).
/memory-exploreLaunches subagent for deep traversal of Forgetful knowledge graph from starting query, summarizing relevant memories, entities, documents, artifacts, relationships, and graph overview.
/memorySearches, loads, and visualizes the knowledge graph of past decisions and session context. Also supports history and status subcommands.
/vault-challengeChallenges a topic or decision by searching your history for counter-evidence and recorded contradictions. Provides a steel-man counter-argument with source citations and logs the result to your vault.