eladkaplan
Joined 6 years ago
Joined 6 years ago
How it works with AI agents:
One command to set up: shellfirm connect claude-code
This gives you two layers of protection:
1. Hooks – automatic pre-execution checks that block dangerous commands before the agent can run them. The agent can't bypass or ignore these.
2. MCP tools – the agent can proactively ask "is this command risky?" and get back structured risk assessments with severity, blast radius, and safer alternatives.
shellfirm covers 9 ecosystems (git, k8s, terraform, databases, filesystem, etc.) with pattern matching, context detection (SSH, root, production branch), and team policies via .shellfirm.yaml.
Supports Claude Code (hooks + MCP), Cursor, Windsurf, Zed, and Cline.
Written in Rust. Open source.
Feels like a superpower for recruiters or hiring managers.
Curious, would you use something like this in your workflow? What would make it more useful or trustworthy?
To address this, I developed the snipdoc tool, which significantly improved the project's ease of maintaining and validating the docs as part of our CI.
I would love to hear your feedback. Thanks!
Now that we're pretty much solid with Loco (https://loco.rs), the "Rust on Rails" framework, we're taking feedback from the community on what they would expect to see on the UI part.
Should it be React based? Dioxus? Yew?
Happy if anyone would like to chip in with their opinion here:
Ossue pulls issues, PRs, and discussions from all your repos into one local inbox. AI analyzes each item automatically: structured triage for issues (bug vs feature, priority, area), code review verdicts for PRs (with breaking change detection), and discussion summaries. You can customize the AI's review criteria per project.
It also has a "notes to issues" workflow, brain dump a rough idea, AI structures it into a proper GitHub issue with title, labels, and priority, then publish directly.