From agent
Displays compact Claude Code agent runtime status: model, context/memory usage, crons, voice, channels. Works in CLI/messaging via /status, /agent:status triggers.
npx claudepluginhub crisandrews/clawcode --plugin agentThis skill uses the workspace's default tool permissions.
Show a compact status card with everything the user needs at a glance. Works from CLI and messaging channels.
Shows OpenClaw-compatible usage cost summary for session, today, last 30 days. Falls back to agent memory, dreams, and resource stats when costs unavailable. Useful for tracking Claude Code sessions.
Provides compact summary of Claude Code Hermit session state from SHELL.md: ID, status, task progress, current step, blockers, budget, cost. --full appends proposals, routines, activity. Triggers on status/progress queries.
Audits Claude Code context window usage across agents, skills, rules, MCP servers, and CLAUDE.md. Detects bloat, redundancy, and recommends prioritized token-saving optimizations.
Share bugs, ideas, or general feedback.
Show a compact status card with everything the user needs at a glance. Works from CLI and messaging channels.
π½ <Name> <emoji>
π§ Model: <model name> (e.g. Opus 4.6)
π Context: <used%> Β· Memory: <N> files, <M> chunks Β· <backend>
π Crons: heartbeat <schedule>, dreaming <schedule>
π Voice: <tts backend> (<enabled|disabled>)
π‘ Channels: <active channels or "none">
Call agent_status MCP tool β gives identity, memory stats, dream data.
Call agent_config MCP tool (action='get') β gives backend, voice, http config.
Get model name β you know your own model. Use the display name (e.g. "Opus 4.6"), not the internal ID.
Get context + session usage β 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 β current model (e.g. "Claude Opus 4.6 (1M context)")context_window.used_percentage β context window usage (0-100)rate_limits.five_hour.used_percentage β 5-hour session usagerate_limits.five_hour.resets_at β epoch when session resetsrate_limits.seven_day.used_percentage β weekly usagerate_limits.seven_day.resets_at β epoch when week resetsIf the file doesn't exist or is stale, fall back to "run /cost for details".
Get cron info β 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 β 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.
π½ **Wally** π½
π§ Model: Opus 4.6 (1M context) Β· Context: 23%
π Memory: 42 files, 120 chunks Β· builtin (QMD vsearch)
β±οΈ Session: 15% (3h 20min left) Β· Week: 8% (Resets Fri, 6:00AM)
π Crons: heartbeat */30, dreaming 3am
π‘ Channels: whatsapp (connected)
Same content, *bold* instead of **bold**. No markdown headers.
Same content, **bold** is fine.
/cost or /usage./mcp.