agentrq/agentrq

AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agents from wherever you want Mobile, Web, Desktop. Designed to work well with your own Claude

★ 1.1k · agentrq/agentrq source on GitHub · this plugin in the registry

agentrq/agentrq is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, can rewrite the system prompt, executes system commands, decodes base64 payloads.

Installable plugin — declares a dsh.bundle manifest

What it can do

Capability	Flag	Evidence
patches the dsh runtime	`runtime_patch`	./cordis.patch.yml
can rewrite the system prompt	`prompt_surface`	systemPrompt
executes system commands	`exec`	×16 in authored code, e.g. desktop/scripts/copyright.mjs:14, desktop/scripts/copyright.mjs:14
decodes base64 payloads	`base64_decode`	×4 in authored code, e.g. desktop/src/main/index.js:1243, desktop/src/main/index.js:1345
starts a network server	`net_server`	×6 in authored code, e.g. desktop/scripts/dev.mjs:64, desktop/scripts/verify-side-panel.mjs:81
reads credential-class env vars	`token_env`	AGENTRQ_ROOT_TOKEN, QA_ROOT_TOKEN

Services it injects

agents systemPrompt tools

Hooks it attaches

agent/disposed agent/status

Outbound domains

agentrq.com app.agentrq.com huggingface.co chromewebstore.googleapis.com api.github.com

Environment variables it reads

SHOTS OFFSCREEN QA_BROWSER_LIBRARY_PATH GITHUB_REF AGENTRQ_ROOT_TOKEN AGENTRQ_SERVER_URL PLAYWRIGHT_DIR AGENTRQ_SERVER_BIN AGENTRQ_DEV_API_TARGET QA_DATA_DIR

How to read this

Levels measure capability surface and transparency, not maliciousness. A C3 plugin can be entirely legitimate — a desktop shell genuinely needs subprocesses. The point is that you can see this before installing. See the levels explained and how dsh plugins work.

Findings come from static analysis of shipped code; nothing is executed. Think a flag is wrong? Open an issue — every flag cites the file and line it came from.