Skip to content
appsgit

Agent Observability

Agent Observability is an agent skill (a SKILL.md file) from BagelHole/DevOps-Security-Agent-Skills. Instrument AI agents with tracing, token metrics, latency, and cost visibility. It works with Claude Code, Codex, Cursor and OpenCode and has 1,141 GitHub stars across a repository of 2 listed skills.

github.com/BagelHole/DevOps-Security-Agent-Skills/devops/ai/agent-observability (opens in a new tab)

View on GitHub (opens in a new tab)

Add this skill

Claude

Claude Code loads skills from ~/.claude/skills/ (all projects) or .claude/skills/ (one project):

git clone --depth 1 https://github.com/BagelHole/DevOps-Security-Agent-Skills.git
cp -r DevOps-Security-Agent-Skills/devops/ai/agent-observability ~/.claude/skills/agent-observability   # personal, or .claude/skills in a project

In the Claude apps, zip the agent-observability folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).

ChatGPT / Codex

Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:

git clone --depth 1 https://github.com/BagelHole/DevOps-Security-Agent-Skills.git
cp -r DevOps-Security-Agent-Skills/devops/ai/agent-observability .agents/skills/agent-observability   # repo; ~/.agents/skills for all projects

Standalone skills also load in the ChatGPT desktop app.

Cursor

Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:

git clone --depth 1 https://github.com/BagelHole/DevOps-Security-Agent-Skills.git
cp -r DevOps-Security-Agent-Skills/devops/ai/agent-observability .cursor/skills/agent-observability   # project; ~/.cursor/skills for all projects

Source (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)

What this skill does

Instrument AI agents with tracing, token metrics, latency, and cost visibility. Use for reliability and debugging. Monitor AI agent behavior with logs, traces, metrics, and cost telemetry. This skill covers the full observability stack for LLM-powered applications: from raw Prometheus counters to Grafana dashboards, OpenTelemetry tracing, structured logging, cost tracking, SLO definition, and PII redaction.

When it triggers

  • Use for reliability and debugging.

More skills in BagelHole/DevOps-Security-Agent-Skills

2 skills are listed from this repository.

Similar skills

More devops & cloud skills

All DevOps & cloud

FAQ

Agent Observability FAQ

Still curious? Email info@appsgit.com.

What is the Agent Observability skill?

Agent Observability is an agent skill (a SKILL.md file) from BagelHole/DevOps-Security-Agent-Skills. Instrument AI agents with tracing, token metrics, latency, and cost visibility. It works with Claude Code, Codex, Cursor and OpenCode and has 1,141 GitHub stars across a repository of 2 listed skills. Its SKILL.md lives at github.com/BagelHole/DevOps-Security-Agent-Skills/devops/ai/agent-observability.

How do I install the Agent Observability skill?

Copy the agent-observability folder (the one containing SKILL.md) into ~/.claude/skills/ for Claude Code, .agents/skills/ for Codex or .cursor/skills/ for Cursor. The agent picks it up automatically when a task matches its description.

Is the Agent Observability skill free?

Yes. The repository is open source under the MIT license.

Is Agent Observability maintained?

The repository's most recent commit was on May 22, 2026. Its latest release is v2.0.0. appsgit only lists skills from repositories with a commit in the last six months.