Skill

agentdb-status

Show AgentDB health — pattern count, embedder status, cache hit rate, learning gain since init. Use when the user asks "is agentdb working?", "how many memories?", "show agentdb stats", or after long-running sessions to confirm state.

npx claudepluginhub ruvnet/agentdb --plugin agentdb-core

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Reports the live state of the AgentDB Cognitive Container backing this session.

SKILL.md

Similar Skills

doctor

Runs diagnostic checks on agent workspace: config, identity, memory, SQLite index, QMD, crons, hooks, HTTP bridge, messaging plugins, dreaming. Auto-fixes with --fix.

agent

memory-stats

Displays statistics and recent entries from Claude Code's persistent memory database, showing session counts, knowledge areas, facts, and activity. Invoke via /memory-stats with optional flags for facts, knowledge, or search.

claude-turbo-search

agentdb-recall

Retrieve relevant memories for the current task from AgentDB. Use at the start of a task to load prior knowledge, when stuck to surface what worked before, or when the user asks "what do we know about X" / "have we done this before?"

agentdb-memory

Stats

Parent Repo Stars37

Parent Repo Forks3

Last CommitMay 6, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

AgentDB Status

Reports the live state of the AgentDB Cognitive Container backing this session.

When to use

User asks "what's in agentdb?", "is the memory working?", "show stats"

Debugging recall quality — high miss rate? cache cold?

Before / after a long session to see how much was learned

CI smoke check before deploying an agent that depends on AgentDB

Steps

Call agentdb_pattern_stats to get pattern count, hit rate, recent insert/search latencies.

If available, call agentdb_reflexion_stats for episode count and per-task win rates.

Call agentdb_bandit_stats (if agentdb-learning is installed) for arm reward summaries.

Render a compact table:

patterns        12,847
episodes           384
skills              22
hit rate          94.2%
avg search       0.83 ms
learning gain   +18% since init
storage           38 MB (.rvf)

If any number looks off (zero patterns, hit rate <50%, latency >10ms), flag it and link to the relevant ADR / docs.

Don't

Don't dump the raw stats JSON — readers want the summary.

Don't infer "broken" from a fresh init (zero patterns is correct on day 0).

AgentDB Status

Reports the live state of the AgentDB Cognitive Container backing this session.

When to use

User asks "what's in agentdb?", "is the memory working?", "show stats"
Debugging recall quality — high miss rate? cache cold?
Before / after a long session to see how much was learned
CI smoke check before deploying an agent that depends on AgentDB

Steps

Call agentdb_pattern_stats to get pattern count, hit rate, recent insert/search latencies.
If available, call agentdb_reflexion_stats for episode count and per-task win rates.
Call agentdb_bandit_stats (if agentdb-learning is installed) for arm reward summaries.

Render a compact table:

patterns        12,847
episodes           384
skills              22
hit rate          94.2%
avg search       0.83 ms
learning gain   +18% since init
storage           38 MB (.rvf)

If any number looks off (zero patterns, hit rate <50%, latency >10ms), flag it and link to the relevant ADR / docs.

Don't

Don't dump the raw stats JSON — readers want the summary.
Don't infer "broken" from a fresh init (zero patterns is correct on day 0).