Three guards that stop an agent's shell commands from destroying work: no stash or discarding checkout, no killing processes by name, and no reading or writing files your settings deny
Plugin safety-hooks from marketplace dorkos in dork-labs/marketplace. Commands read from the repo's manifest — 2 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
cd "${CLAUDE_PROJECT_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}" && node "${CLAUDE_PLUGIN_ROOT}/hooks/file-guard.mjs"
cd "${CLAUDE_PROJECT_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}" && node "${CLAUDE_PLUGIN_ROOT}/hooks/git-guard.mjs"
cd "${CLAUDE_PROJECT_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}" && node "${CLAUDE_PLUGIN_ROOT}/hooks/process-guard.mjs"
The /flow workflow engine: a PM-agnostic, dual-mode (manual and autonomous) system that carries product work from capture to done across one stage spine, with a runnable-TypeScript engine and a pluggable tracker adapter.
20 skills · 15 commands · hooks
Four skills for writing that people and agents can use: plain-language user copy, architecture decision records, developer guides, and clarifying questions before work starts
4 skills
Label throwaway containers, VMs and sandboxes, and sweep them from the next run: exit handlers do not survive a kill
1 skill
Guides AI agents through developing, validating, and publishing DorkOS marketplace packages
1 skill
Your agent shows you screens, mockups and clickable prototypes beside the chat. Pin a note on the exact spot you want changed, press Send, and it gets to work. It runs on this computer only, with no share or guest links. Any page this renders can message the agent that owns it. Don't open pages you don't trust.
1 skill
Your Linear issues on the dashboard. After you approve its schedule, the agent checks your Linear inbox every 15 minutes.
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.
7 skills · 1 command · 3 agents
CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 1 MCP server · hooks
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Headroom startup hooks for Claude Code and GitHub Copilot CLI.
hooks
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.