From agent
Shows agent runtime status including identity, model, context usage, memory stats, crons, and voice configuration. Triggers on /status or natural language requests.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent:statusThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Show a compact status card with everything the user needs at a glance. Works from CLI and messaging channels.
Show a compact status card with everything the user needs at a glance. Works from CLI and messaging channels.
👽 <Name> <emoji>
🧠 Model: <model name> (e.g. Opus 4.6)
📊 Context: <used%> · Memory: <N> files, <M> chunks · <backend>
🕐 Crons: heartbeat <schedule>, dreaming <schedule>
🔊 Voice: <tts backend> (<enabled|disabled>)
📡 Channels: <active channels or "none">
Call agent_status MCP tool — gives identity, memory stats, dream data.
Call agent_config MCP tool (action='get') — gives backend, voice, http config.
Get model name — you know your own model. Use the display name (e.g. "Opus 4.6"), not the internal ID.
Get context + session usage — the statusline script writes the latest Claude Code runtime data to /tmp/claude-statusline-latest.json. Read it:
cat /tmp/claude-statusline-latest.json 2>/dev/null
This JSON contains:
model.display_name — current model (e.g. "Claude Opus 4.6 (1M context)")context_window.used_percentage — context window usage (0-100)rate_limits.five_hour.used_percentage — 5-hour session usagerate_limits.five_hour.resets_at — epoch when session resetsrate_limits.seven_day.used_percentage — weekly usagerate_limits.seven_day.resets_at — epoch when week resetsIf the file doesn't exist or is stale, fall back to "run /cost for details".
Get cron info — Bash: jq '.entries | length' memory/crons.json 2>/dev/null || echo 0 to count active registry entries. Optionally: jq '[.entries[] | select(.paused == false and .tombstone == null)] | length' memory/crons.json for the expected-alive count.
Get channel info — if channels_detect MCP tool is available, call it. Otherwise check ls ~/.claude/plugins/cache/ 2>/dev/null for installed plugins.
Build the card using REAL data. Never fabricate numbers.
👽 **Wally** 👽
🧠 Model: Opus 4.6 (1M context) · Context: 23%
📊 Memory: 42 files, 120 chunks · builtin (QMD vsearch)
⏱️ Session: 15% (3h 20min left) · Week: 8% (Resets Fri, 6:00AM)
🕐 Crons: heartbeat */30, dreaming 3am
📡 Channels: whatsapp (connected)
Same content, *bold* instead of **bold**. No markdown headers.
Same content, **bold** is fine.
/cost or /usage./mcp.npx claudepluginhub crisandrews/clawcode --plugin agentRuns diagnostic checks on agent workspace: config, identity, memory, SQLite index, crons, hooks, HTTP bridge, messaging plugins, and dreaming. Supports --fix for safe auto-repairs. Use after agent create/import or when something feels off.
Displays Honcho memory system status: connection health, workspace, peers, observation queue, and conclusion count. Invoke via /honcho:status for quick checks.
Discovers and communicates with active AI agents (Codex, Claude Code) using ai-devkit agent list, detail, and send commands. Useful for inter-agent coordination.