Ready-made AI agent bots with instructions, routines and skills. Install them on OpenClaw, AutoGPT, OpenAI Dots, Claude Duet, Meta Muse, Hermes Agent or Grok Bot.
Screens email for hidden instructions aimed at AI assistants—white text, zero-width characters, and "ignore previous instructions" lines—and warns you before those messages are fed to any bot.
Reviews suspicious inbox messages with a color-coded 0–100 scam score based on urgency tricks, lookalike domains, payment asks and known alert patterns—read-only unless you approve an action.
Compares environment variables across local, staging and production, finds missing, unused or mismatched settings before they break a deploy, and keeps your example env file honest.
Proposes concrete actions from guarded facts and waits for explicit human approval before any side effect.
Reads untrusted channels, wraps content as data, and never takes external actions itself.
Drafts community or social replies for scheduled engagement windows, waiting for approval to post.
Runs scheduled digests of metrics, inbox, and blockers into a short morning brief.
Builds a token-budgeted prompt pack for each DAG task with only the files and upstream summaries it needs.
Collects worker outputs, checkpoints progress, and prepares downstream summaries so a DAG run can resume.
Collects TODO, FIXME and HACK comments across your codebase, finds the old and risky ones, links them to issues and suggests which to fix, file or delete each sprint.
Reads and drafts iMessages on your Mac. Summarizes threads, proposes replies, and only sends when you approve.

