Skip to main content
plugin CX Codex

sre-extension — Claude Code plugin: what it does, how to install

The sre-extension plugin for Claude Code supports Google Cloud outage investigations, log analysis, and post-mortem generation.

Apache-2.0 ★ 151 updated 2026-10-12

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add gemini-cli-extensions/sre
/plugin install sre-extension@sre
Open on GitHub

What sre-extension does

This plugin equips your coding assistant with SRE incident workflows for GCP and GKE. Starting from investigation-entrypoint, the assistant queries Cloud Logging, pulls metric time series via the Cloud Monitoring API, and flags unexpected spikes using Isolation Forest, KNN, or Z-score algorithms.

It bundles tools for Cloud Build error triage, automated setup for Google Managed MCP servers, and Python scripts that draw annotated outage charts for post-mortems. Without python and uv present on your system, the analytical and graphing tools will fail to run.

What it helps with

  • diagnose production outages across GCP and GKE infrastructure
  • configure Google Managed MCP servers for Cloud Logging and Monitoring
  • detect time-series anomalies using Isolation Forest and Z-score methods
  • produce incident post-mortems complete with annotated Python charts

Example prompts for the agent

  • /investigation-entrypoint investigate high error rate on Cloud Run
  • /gcp-mcp-setup configure MCP access for Cloud Logging and GKE
  • /postmortem-generator generate a post-mortem report for the latest outage

How to install sre-extension

Plugin marketplace

/plugin marketplace add gemini-cli-extensions/sre
/plugin install sre-extension@sre

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about sre-extension

How to install sre-extension in Claude Code?

Run both marketplace commands in sequence: first /plugin marketplace add gemini-cli-extensions/sre, then /plugin install sre-extension@sre.

What does sre-extension do?

It gives the CLI agent specialized skills to navigate GCP architecture, follow mitigation playbooks, track SLOs, and draft post-mortems.

What prerequisites are required?

You need python and the uv package runner installed locally to execute data ingestion and graph generation.

Source text

SKILL.md · Apache-2.0
<p align="center">
  <img src="docs/sre-extension-logo.png" width="400" alt="SRE Extension Logo">
</p>

> **Note:** Given the recent [deprecation of Gemini CLI](https://developers.googleblog.com/an-important-update-transitioning-gemini-cli-to-antigravity-cli/), this Extension is also fully functional as a Plugin for [agy CLI](https://antigravity.google), Claude Code, and Codex.


# About

**The SRE Gemini CLI Extension** is a dedicated toolkit comprising specialized **Skills** designed to augment Site Reliability Engineers (SREs). By integrating deeply with the Gemini CLI, this extension empowers SREs to investigate outages, configure MCP servers, formulate mitigations, and detect anomalies more rapidly.

See also:
* [Reference PostMortems](https://github.com/palladius/about-sre-extension/) we've created with this tool.
* [SRE Testing Suite](https://github.com/palladius/sre-testing-suite) to test your setups (currently a work in progress) and its related **[Codelab](https://codelabs.developers.google.com/codelabs/investigate-gke-cluster-breakage-scenarios-with-postmortem#0)**.

## 📺 Demo Outage Investigation

Watch the **SRE Extension** in action as it performs a live production outage investigation and generates a detailed PostMortem:

[![SRE Extension Demo Outage Investigation](docs/sre-demo-video-thumbnail.png)](https://youtu.be/bPCznsjW8BU)


## Installation

For detailed installation and configuration instructions across all CLI environments, please refer to the [Installation Guide (INSTALL.md)](INSTALL.md).

If you have [`just`](https://github.com/casey/just) (a modern `make` clone) installed, you can quickly set up the extension. If you don't have `just` yet, you can quickly install it via `brew install just` / 
`sudo apt-get install just` (or see [casey/just](https://github.com/casey/just#installation) for more options).

Once installed:

```bash
# Google Antigravity CLI (agy)
just install-agy
# Google Gemini CLI (deprecated)
just install-gemini
# Claude Code
just install-claude
# GitHub Copilot CLI
just install-copilot-persistent
```

You also need `python` and `uv` installed.


## Available Skills

### 🛠️ Core SRE Skills
- **`investigation-entrypoint`**: Primary entrypoint for investigating production outages, orchestrating SRE response, and mitigating incidents. Start here when an incident occurs!
- **`gcp-architecture-discovery`**: Discover and map GCP infrastructure architecture including compute, networking, storage, and service dependencies.
- **`gcp-playbooks`**: Follows established SRE playbooks for GCP/GKE investigations, including infrastructure discovery and common mitigation steps.
- **`gcp-mcp-setup`**: Automates enabling services, Google Managed MCP (OneMCP) servers, generating API keys, and configuring the MCP settings file for your CLI harness (Gemini, Antigravity, or Copilot).
- **`gcp-slo-management`**: Discover Monitoring Services, list existing SLOs, or create new SLOs (Availability/Latency) via the REST API.
- **`postmortem-generator`**: Creates a generated PostMortem given enough context about a resolved incident/outage.

### ☁️ Cloud Capabilities
- **`cloud-build-investigation`**: Expert-level SRE skill for Google Cloud Build (GCB) and Cloud Run investigations. Correlates git commits with build failures and analyzes logs.
- **`cloud-logging`**: Skill for interacting with and analyzing Google Cloud Logging and Error Reporting. Processes large JSON logs or converts them to Apache format.
- **`cloud-monitoring`**: Interacts with Google Cloud Monitoring via APIs to avoid large context bloat. Exports time-series data and helps setup SLOs.

### 📊 Detection, Graphs & Mitigations
- **`generic-mitigations`**: Generic Mitigations high-level classification logic and actuation plan.
- **`monitoring-graphs`**: Generates high-quality, annotated incident graphs for post-mortems using Python to visualize outages and error rates (nice graphs visible [here](https://github.com/palladius/about-sre-extension/)).
- **`anomaly-detection`**: Detects anomalies in time-series data from various sources (Isolation Forest, KNN, Z-score).
- **`data-ingestion`**: Fetches and parses time-series data from various sources for downstream analysis.

## Compatibility & Harness Support

| Capability            | Gemini CLI | Antigravity (`agy`)                                      | Claude Code                                              | Codex                                                    | Copilot CLI                                              |
| :----------------------| :----------:| :--------------------------------------------------------:| :--------------------------------------------------------:| :--------------------------------------------------------:| :--------------------------------------------------------:|
| **Type**              | Extension  | [Plugin](https://antigravity.google/docs/plugins) | [Plugin](https://code.claude.com/docs/en/plugins-reference) | [Plugin](https://developers.openai.com/codex/plugins) | [Plugin](https://docs.github.com/copilot/how-tos/copilot-cli/customize-copilot/plugins-creating) |
| **Install**           | ✅          | ✅                                                        | ✅                                                        | 🟢                                                        | ✅                                                        |
| **MCP Setup**         | ✅          | ✅                                                        | 🟢                                                        | 🟢                                                        | ✅                                                        |
| **SRE Skills**        | ✅          | ✅                                                        | 🟢                                                        | 🟢                                                        | ✅                                                        |
| **GKE Investigation** | ✅          | ✅                                                        | 🟢                                                        | 🟢                                                        | 🟢                                                        |

**Legend:** ✅ Works (Tested) | 🟢 Works (Untested) | 🔴 Doesn't Work (Red Flag)

## Quickstart

1. Install this extension by following the instructions in [INSTALL.md](INSTALL.md).
2. Only for the first time, use `gcp-setup` and `gcp-mcp-setup` skills to ensure your GCP project and MCP servers are set up correctly:
   ```bash
   $ agy
   /gcp-setup Setup my GCP project "foo-bar-123"
   with email `[email protected]`.
   [..]
   /gcp-mcp-setup Also set up MCP access to Cloud Logging,
   Cloud Monitoring, GKE and Documentation (Developer Knowledge). Skip
   BQ and Cloud Run for this time.
   ```
3. Invoke the entrypoint skill with your incident request. For example:
   ```bash 
   $ agy
   /investigation-entrypoint Use investigation entrypoint skill
   with this new incident: GKE cluster with frontend 1.2.3.4 is reported 
   down by numerous customers, please investigate.
   ```
4. The agent will take it from there—fetching context, querying metrics, and formulating mitigations.

For detailed instructions on setup and usage, please refer to the [User Manual](USER_MANUAL.md).


## Contributing

Check `CONTRIBUTING.md`.



## 🗺️ Public Resources Map

Here is a visual map showing how the SRE Extension codebase, testing suite, postmortems, and learning tutorials relate to each other:

![Public SRE Resources Map](docs/public-resources-map.png)

For a detailed description of the mappings, see [docs/public-resources-map.md](docs/public-resources-map.md).

## Feedback 

For feedback, please report **bugs** and **feature requests** in the issue tracker.
Any other intelligible feedback should be sent to this form: [SRE Extension Survey](https://forms.gle/eJPrbG4KKESp6GmF6)

# Thanks

Program Lead: [Riccardo](https://github.com/palladius)

Co-authors and contributors:
- [Madhavi](https://github.com/madkarra)
- [Ramón](https://github.com/rmedranollamas)
- [Szymon](https://github.com/szymonst)
<!-- add your name here -->

© Google · Apache-2.0 · gemini-cli-extensions/sre

Similar plugins

All plugins for Cloud: AWS, Azure, GCP →

From the same set17

The whole set →
postmortem-aggregator postmortem-aggregator turns Post Mortem files in a folder into incident statistics and updates POMO_AGGREGATED.md. Use it to spot recurring causes across incidents. CX Codex +1 ★ 151repo stars gcp-mcp-setup gcp-mcp-setup — a skill for Claude Code, Codex, and Gemini CLI that wires up Google Managed MCP servers (OneMCP) to your CLI environment. It enables APIs, generates an API key, and writes the MCP config to the right settings file. CX Codex +1 ★ 151repo stars generic-mitigations generic-mitigations guides your agent to halt production outages quickly using standard SRE strategies before diving into root-cause analysis. CX Codex +1 ★ 151repo stars monitoring-graphs monitoring-graphs — a skill for Claude Code, Codex and Gemini CLI that generates annotated incident graphs in Python. Use it to visualize outages, plot error spikes, or correlate metrics with incident milestones. CX Codex +1 ★ 151repo stars anomaly-detection anomaly-detection detects outliers in time-series metrics from CSV, cloud monitoring, and other sources. Chooses smoothing and algorithms automatically, or accepts your tuning parameters. CX Codex +1 ★ 151repo stars investigation-entrypoint The investigation-entrypoint skill for Claude Code, Codex, and Gemini CLI coordinates GCP incident investigations across GKE and Cloud Run. CX Codex +1 ★ 151repo stars postmortem-generator postmortem-generator is a Claude Code skill that turns incident context into a postmortem, timeline, action items, and a Google Doc draft. It starts after investigation and root-cause work. CX Codex +1 ★ 151repo stars gcp-architecture-discovery gcp-architecture-discovery — a skill that walks a GCP project outward from the service that broke and writes down what it finds: compute, networks, databases, buckets. The map stays on disk between sessions. CX Codex +1 ★ 151repo stars

Project sponsors

Companies that keep this analytics open