CTX Dashboard

System Health

Activity events / minute (last 2h)

Retrieval method breakdown last graph window

loading…

Latency distribution bm25-memory hook

Utility rate share of injected items Claude actually referenced ⓘ how

Code files G2-PREFETCH / G2-GREP — code files discovered by CTX on recent turns

loading…

Token Usage CTX-injected tokens per turn

loading…

Quality notices rate-based, informational

Other signals

Knowledge graph decisions · docs · prompts — coral = selected prompt, edges = retrieval + topic + temporal

Function proof — real samples recent prompts → actual hook outputs (eye-check relevance)

Per-prompt utility pill:

≥50% CTX surfaced items Claude actually used ≥25% partially used <25% injected but not referenced — honest signal, not a bug — reply not yet persisted (Stop hook fires ~30s after turn)

System Health

Activity events / minute (last 2h)

Retrieval method breakdown last graph window

Latency distribution bm25-memory hook

Utility rate share of injected items Claude actually referenced ⓘ how

Code files G2-PREFETCH / G2-GREP — code files discovered by CTX on recent turns

Token Usage CTX-injected tokens per turn

Quality notices rate-based, informational

Other signals

Knowledge graph decisions · docs · prompts — coral = selected prompt, edges = retrieval + topic + temporal refresh

Function proof — real samples recent prompts → actual hook outputs (eye-check relevance) refresh

Recent events newest first, last 30

Knowledge graph decisions · docs · prompts — coral = selected prompt, edges = retrieval + topic + temporal

Function proof — real samples recent prompts → actual hook outputs (eye-check relevance)