ship
01Command Claude Code
Create a new git branch, commit changes, and create a pull request.
39 tagged observability, measured the same way as everything else here.
Browse within: agent-evaluation 12opentelemetry 12Autonomous Agents 5code-quality 5duckdb 5
Command Claude Code
Create a new git branch, commit changes, and create a pull request.
Command Claude Code
Use this command before changing organisation, project, or database config behavior.
Command Claude Code
Use this command before handing off security-sensitive OpenLIT changes.
Command
Commit the staged changes with a conventional commit message.
Command Codex
I made changes in the langfuse/langfuse repository. I want to update the documentation in this repository to reflect those changes.
nexus-labs-automation/mobile-observability
Command
Scan a codebase for existing observability instrumentation and identify gaps.
nexus-labs-automation/mobile-observability
Command
Generate a comprehensive instrumentation plan for a mobile codebase.
Command
List recent sessions on this project by agent — peers (Codex, OpenClaw, Copilot CLI) or your own.
Command
Search past agent sessions on this project by keyword, or read one session by id.
Command Claude Code
The user wants to create a harness experiment config to test a hypothesis about agent behavior. Your job is to design the experiment, write a config, run it, and analyze the results.
Command
Show TokenJam's savings/optimize report — where quota is going and what's recoverable. Equivalent to running tj optimize.
Command
Show TokenJam's current status for every tracked agent — token usage, cost today, and active alerts. Equivalent to running tj status.
Command
Remove TokenJam's Claude Code integration — unwires the statusline, hooks, and OTel env vars that /onboard set up. Equivalent to running tj uninstall --yes. Does not remove the plugin itself.
Command Claude Code
This document describes the standard release process for agtrace.
Command
Advanced history search and analysis for AI coding agent sessions.
Command
Inspect and query historical AI coding agent sessions.
Command Claude Code
Follow the project management workflow defined in .agents/skills/project/SKILL.md.
Command Claude Code
Reset all workflow data from Postgres, pg-boss, and ClickHouse.
Command
View or change Self-Care configuration settings.
Command
Review unreviewed reports — walk through findings and categorize them.
Command
Main entry point — run the full pipeline (validate, analyze, report, review, summarize).
Command
Cost and tool-output report. Retrieve a stashed original with scrim get.
karsten-s-nielsen/mad-scientist-skills
Command
Round 2+ review — confirm revisions landed, catch regressions, do not re-litigate.
karsten-s-nielsen/mad-scientist-skills
Command
Unbiased review of another session's implementation (diff, staged, or branch).