Skill

productionos-stats

Display ProductionOS system statistics — agent count, command count, hook count, test count, version, instinct count, and session history.

Install

npx claudepluginhub shaheerkhawaja/productionos --plugin productionos

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Display ProductionOS system statistics — agent count, command count, hook count, test count, version, instinct count, and session history.

SKILL.md

Similar Skills

skill-lookup

Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.

prompts.chat

157.6k

prompt-lookup

Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.

prompts.chat

157.6k

Agent Development

6 files

Guides agent creation for Claude Code plugins with file templates, frontmatter specs (name, description, model), triggering examples, system prompts, and best practices.

plugin-dev

83.2k

Stats

Stars6

Forks2

Last CommitApr 14, 2026

Actions

View Source View Plugin View on GitHub View README

productionos-stats

Display ProductionOS system statistics — agent count, command count, hook count, test count, version, instinct count, and session history.

Inputs

Parameter	Values	Default	Description
`target`	path or context	cwd	What to operate on

/productionos-stats — System Dashboard

Display a comprehensive stats dashboard for the current ProductionOS installation.

Step 0: Preamble

Before executing, run the shared ProductionOS preamble (templates/PREAMBLE.md).

Step 1: Run Stats Dashboard

Execute the stats dashboard script:

bun run scripts/stats-dashboard.ts

The script computes and outputs all metrics in structured markdown format.

Metrics Computed

System Metrics

Version — from VERSION file
Agent count — total .md files in agents/ with HIGH/MEDIUM/LOW stakes breakdown
Command count — total .md files in .claude/commands/
Hook count — unique hook scripts referenced in hooks/hooks.json
Template count — total .md files in templates/
Script count — total .ts files in scripts/
Test file count — total .ts files in tests/

Learning Metrics

Project instincts — patterns learned for the current project
Global instincts — cross-project patterns (confidence > 0.8)
Session handoffs — auto-generated handoff documents
Skill usage events — total events in analytics log

Git Activity

Total commits — git rev-list --count HEAD
Commits today — git log --oneline --since=midnight
Last handoff — most recent session handoff document

Output Format

The dashboard outputs a markdown table for each category, suitable for display in Claude Code's conversation.

Use Cases

Run after a sprint to see what was shipped (new agents, commands, hooks)
Check learning progress (instinct accumulation across sessions)
Verify installation completeness (all counts match expected values)
Share stats in session handoff documents for continuity

Error Handling

Scenario	Action
No target provided	Ask for clarification with examples
Target not found	Search for alternatives, suggest closest match
Missing dependencies	Report what is needed and how to install
Permission denied	Check file permissions, suggest fix
State file corrupted	Reset to defaults, report what was lost

Guardrails

Do not silently change scope or expand beyond the user request.
Prefer concrete outputs and verification over abstract descriptions.
Keep scope faithful to the user intent.
Preserve existing workflow guardrails and stop conditions.
Verify results before concluding.