# Lightrun

> Lightrun's runtime investigation toolkit for Claude Code. Guides deterministic, evidence-first debugging of live applications by capturing real production behavior — variable state, stack traces, and execution flow — without redeploys or service restarts. Includes a mandatory preflight check that grounds investigations in actual runtime evidence, plus a blocker-aware handoff format that produces structured, reproducible debugging reports for engineering teams.

## Facts
- Page: https://tashan.sh/capability/plugin-lightrun-platform-lightrun-ai-lightrun
- tashan id: plugin:lightrun-platform/lightrun-ai/lightrun
- Source: https://github.com/lightrun-platform/lightrun-ai
- Type: plugin
- Category: ai
- tashan score: 55.0 / 100
- Adoption: 26.0
- Upkeep: 93.0
- Freshness: 84.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: thin
- GitHub stars: 27
- Official: no

## Install

```sh
/plugin marketplace add anthropics/claude-plugins-community
/plugin install lightrun@claude-community
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-09-13 by tashan (https://tashan.sh) from public evidence. Scorer s5.