Evangelosmeklis Thufir
Thufir is a Claude Code plugin for the Operate phase that structures production incident investigation and root-cause analysis with DevOps and monitoring context.
by evangelosmeklis · github.com/evangelosmeklis/thufir
Run guided root-cause analysis on live production incidents from Claude Code with monitoring and Git context wired in.
Add it to Claude Code
Install the plugin in Claude Code. One command, paste-ready.
/plugin install evangelosmeklis-thufir@evangelosmeklis/thufirBuilt to be called by your agent
Skillselion is itself an MCP server. Your agent can pull this entry and a paste-ready install config straight from the API - no copy-paste.
Retrieve this entry with skillselion.get_details("plugin:evangelosmeklis/thufir") and the paste-ready config with skillselion.get_install_config("plugin:evangelosmeklis/thufir").
What it does
Thufir is a Claude Code plugin bundle aimed at solo builders and small teams who need to move from “something broke in prod” to a structured investigation without leaving the agent. The catalog positions it squarely in operations: debugging, incident response, root-cause analysis, and ties to observability signals such as Prometheus and broader monitoring practice. For an indie operator wearing the SRE hat, that means Claude can help narrate hypotheses, correlate deploys and commits via GitHub or GitLab, and keep the conversation anchored on production facts instead of random code edits. It is not a generic coding assistant skill—it is an incident companion. Expect to use it when alerts fire, error budgets shrink, or users report regressions after a ship. Complexity is intermediate because you need real production access, sensible monitoring, and comfort delegating investigation steps to an agent. With a modest community footprint (7 GitHub stars in catalog metadata), treat it as a specialized Operate tool rather than a mainstream marketplace staple.
Highlights
- Claude Code plugin focused on production incidents and root-cause analysis (RCA)
- Keywords surface Prometheus, monitoring, SRE, and incident-response workflows
- Integrates investigation with GitHub and GitLab for change and deploy context
- DevOps-oriented plugin bundle (1 plugin) from evangelosmeklis/thufir
- Suited to post-deploy stabilization rather than feature shipping
Why builders use it
When production breaks, solo builders waste hours context-switching between logs, metrics, Git history, and chat without a repeatable RCA workflow inside Claude Code.
After you register the plugin, Claude can drive a more consistent incident investigation narrative tied to monitoring, Git hosts, and production-debugging keywords instead of ad-hoc guesses.
At a glance
- Type - Plugin in DevOps.
- Adoption - 0 installs, 7 stars, 0 votes.
FAQ
Who is Thufir for?
Thufir is for solo builders and small teams acting as their own SRE who use Claude Code during production outages and need structured RCA with DevOps and monitoring context.
When should I use Thufir?
Use Thufir when an alert fires, customers report a prod regression, or you are writing a postmortem and want the agent to help investigate cause, not when scaffolding a new feature.
How do I add Thufir to my agent?
Install or register the evangelosmeklis/thufir Claude Code plugin from the repository bundle (1 plugin), then invoke it from Claude Code with access to your monitoring and Git remotes as your setup allows.
Comments
Share how you use evangelosmeklis-thufir, gotchas, or tips for other indie builders.
No comments yet - be the first to share how you use it.