How do I install the Session Monitoring skill?

Run npx skillmds@latest add mercurialsolo/session-monitoring in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Session Monitoring safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Session Monitoring?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Session Monitoring free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Session Monitoring?

mercurialsolo (@mercurialsolo) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Session Monitoring by mercurialsolo

Name: Session Monitoring
Author: mercurialsolo

File contents

claudectl Session Monitoring

You have access to claudectl, a local session supervisor for Claude Code. Use it when the user asks about:

How many sessions are running, their status, or what they're doing
Session costs, burn rates, or budget tracking
Session health (cognitive rot, loops, stalls, context saturation)
Brain decisions, learning progress, or accuracy
File conflicts between sessions
Multi-session orchestration

Available CLI Flags

# Setup
claudectl --init                   # Wire up Claude Code hooks (one-time)
claudectl --init -s project        # Wire up hooks for this project only
claudectl --uninstall              # Remove claudectl hooks

# Session status
claudectl --list                   # Human-readable session list
claudectl --json                   # Machine-readable JSON with full data
claudectl --watch                  # Stream status changes

# Cost and history
claudectl --stats --since 24h     # Aggregated statistics
claudectl --history --since 24h   # Completed session history
claudectl --summary --since 8h    # Activity summary

# Brain
claudectl --mode status     # Show current brain gate mode
claudectl --mode on         # Brain evaluates tool calls (default)
claudectl --mode off        # Disable brain gate
claudectl --mode auto       # Brain auto-approves above threshold
claudectl --brain-stats accuracy  # Per-tool accuracy breakdown
claudectl --brain-stats learning-curve  # Correction rate over time
claudectl --brain-stats baseline  # Brain vs static rules comparison
claudectl --brain-stats false-approve   # Safety: false positive rate

# Diagnostics
claudectl --doctor                # Check terminal integration
claudectl --brain-prompts         # List prompt template sources

Health Check Icons

When reporting session health from JSON output, these are the severity indicators:

Critical: cognitive rot (score > 70), context > 90%, error loops
Warning: context > 80%, cost spikes, stalls, early decay
Info: proactive compaction suggestion, low cache

Key Fields in JSON Output

Each session in --json output includes:

status: NeedsInput, Processing, Waiting, Idle, Finished
cost_usd: total session cost
burn_rate_per_hr: current spend rate
context_tokens / context_max: context window usage
decay_score: 0-100 cognitive health score
has_file_conflict: boolean for cross-session conflicts
pending_tool_name / pending_tool_input: what's waiting for approval

---name: session-monitoringdescription: Provides awareness of claudectl session state, health checks, and cost tracking. Activated when the user asks about session health, spending, brain decisions, or multi-session coordination.---# claudectl Session MonitoringYou have access to claudectl, a local session supervisor for Claude Code. Use it when the user asks about:- How many sessions are running, their status, or what they're doing- Session costs, burn rates, or budget tracking- Session health (cognitive rot, loops, stalls, context saturation)- Brain decisions, learning progress, or accuracy- File conflicts between sessions- Multi-session orchestration## Available CLI Flags```bash# Setupclaudectl --init # Wire up Claude Code hooks (one-time)claudectl --init -s project # Wire up hooks for this project onlyclaudectl --uninstall # Remove claudectl hooks# Session statusclaudectl --list # Human-readable session listclaudectl --json # Machine-readable JSON with full dataclaudectl --watch # Stream status changes# Cost and historyclaudectl --stats --since 24h # Aggregated statisticsclaudectl --history --since 24h # Completed session historyclaudectl --summary --since 8h # Activity summary# Brainclaudectl --mode status # Show current brain gate modeclaudectl --mode on # Brain evaluates tool calls (default)claudectl --mode off # Disable brain gateclaudectl --mode auto # Brain auto-approves above thresholdclaudectl --brain-stats accuracy # Per-tool accuracy breakdownclaudectl --brain-stats learning-curve # Correction rate over timeclaudectl --brain-stats baseline # Brain vs static rules comparisonclaudectl --brain-stats false-approve # Safety: false positive rate# Diagnosticsclaudectl --doctor # Check terminal integrationclaudectl --brain-prompts # List prompt template sources```## Health Check IconsWhen reporting session health from JSON output, these are the severity indicators:- Critical: cognitive rot (score > 70), context > 90%, error loops- Warning: context > 80%, cost spikes, stalls, early decay- Info: proactive compaction suggestion, low cache## Key Fields in JSON OutputEach session in `--json` output includes:- `status`: NeedsInput, Processing, Waiting, Idle, Finished- `cost_usd`: total session cost- `burn_rate_per_hr`: current spend rate- `context_tokens` / `context_max`: context window usage- `decay_score`: 0-100 cognitive health score- `has_file_conflict`: boolean for cross-session conflicts- `pending_tool_name` / `pending_tool_input`: what's waiting for approval

Frequently asked questions

Session Monitoring