From lacp-hardening
Hardens production agent sessions with pretool guards blocking rm -rf, data exfiltration, unsafe publishes; continuous QA running tests every N file writes; git state and focus context injection. Auto-activates via hooks.
npx claudepluginhub 0xnyk/lacp --plugin lacp-hardeningThis skill uses the workspace's default tool permissions.
This plugin provides three layers of production hardening:
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Checks Next.js compilation errors using a running Turbopack dev server after code edits. Fixes actionable issues before reporting complete. Replaces `next build`.
This plugin provides three layers of production hardening:
Blocks dangerous operations before they execute:
rm -rf → suggests trash insteadnpm/cargo/pip publish without approvalcurl | python/node download-first patternschmod 777 → suggests specific masksgit reset --hard, git clean -fcurl --data @.envRuns your project's test command at configurable intervals during work:
Injects at every session start:
| Env Var | Default | Purpose |
|---|---|---|
LACP_EVAL_CHECKPOINT_ENABLED | 0 | Enable continuous QA |
LACP_EVAL_CHECKPOINT_INTERVAL | 10 | Test every N writes |
LACP_CONTEXT_MODE | `` | Active mode (tdd, debugging, sprint, etc.) |