agent-shell
Allows engineers to run LLM agents directly within their editor workflow, reducing context-switching and enabling faster iteration on code generation and deb…
A native Emacs buffer to interact with LLM agents powered by ACP
- Ask Claude to generate shell commands and execute them directly in your Emacs workflow
- Automate repetitive development tasks by having Claude write and run scripts interactively
- Debug code issues by letting Claude examine files and run diagnostics in your editor
Allows engineers to run LLM agents directly within their editor workflow, reducing context-switching and enabling faster iteration on code generation and debugging tasks without leaving the development environment.
Emacs-based development teams seeking tighter integration between code editing and AI-assisted coding workflows.
https://github.com/xenodium/agent-shell
By xenodium
How to Get It
claude plugins install xenodium/agent-shell
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Generate shell commands and execute them directly in my Emacs workflow
Trust Signals Auto-scanned
Community Pulse New
- Emacs agent-shell (powered by ACP) — Hacker News · 233 pts
- Agent-Shell 0.55 Updates — Hacker News · 62 pts
- Agent-shell: A native Emacs buffer to interact with LLM agents powered by ACP — Hacker News · 37 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 1,704 GitHub stars; contributors unknown; last commit 0d ago; license GPL-3.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
- License (GPL-3.0) may restrict commercial use. Check with your legal team.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 1,704 GitHub stars; contributors unknown; last commit 0d ago; license GPL-3.0.