From zeropath
Trigger ZeroPath's cloud AI to investigate whether a finding is exploitable.
How this skill is triggered — by the user, by Claude, or both
Slash command
/zeropath:investigateThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Thin entrypoint. The full request-poll-summarize flow lives in the
Thin entrypoint. The full request-poll-summarize flow lives in the
zeropath-investigator subagent.
Spawn the subagent immediately. Don't probe config/creds/CLI - auto-bootstrap handles those.
Use the Agent tool with subagent_type: "zeropath-investigator".
Brief it with:
~/.zeropath-agent-plugin/repo-binding.json
(subagent uses it to scope batch filters by default - "investigate
the criticals" means this repo, not the whole org)Target shapes the subagent accepts:
id (/zeropath:investigate issue_abc123)Investigations are not free - they trigger real backend work. The subagent requires explicit confirmation before requesting; don't try to streamline that out.
npx claudepluginhub zeropathai/zeropath-agent-plugin --plugin zeropathProvides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.