Investigate reported auth, credential, permission, API proxy, 401, 403, 503, OAuth, token, or secret-resolution failures by querying VictoriaLogs first. Use when a user says an integration auth failed, a tool got unauthorized/forbidden/service unavailable, an api-proxy request failed, or asks why credentials/secrets…
Use Centaur's indexed company context and scoped read-only SQL together with direct Slack, Linear, Google Docs, Drive, Calendar, or Granola searches when answering internal company-history, prior-decision, project-context, meeting-context, roadmap/status, or cross-source memory questions. Indexed context includes…
Scaffold and build new tool integrations in tools/. Use when asked to create a new tool, add an API integration, or build a new client for an external service.
Use the DocSend CLI to recover and download standalone DocSend documents or files from DocSend Spaces, including email or passcode gates, resumable verification, folder traversal, and returning files. Trigger whenever a user shares a DocSend URL or asks to access, inspect, summarize, download, or recover a DocSend…
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -…
Add, modify, or debug Centaur harness-server backends in crates/harness-server. Use when adding support for a new harness CLI, changing Codex App Server V2 normalization, investigating Claude Code/Amp/Codex streaming or steering behavior, removing Python/TypeScript harness normalizers, or differentially testing real…
Researches, plans, implements, validates, and opens a focused PR for one selected self-improvement gap. Use when executing one chosen backlog item from the nightly self-improvement workflow.
Analyzes a day of Slack-thread user sessions to discover opportunities for new skills, personas, tools, workflows, and system-level improvements. Use alongside gap-analysis for the nightly self-improvement workflow.
Smoke test the full running Centaur system from a new Slack thread. Use when asked to QA the stack, run a smoke test, verify a deployment, check stack health, check deploy readiness, or prove Slack tools, file upload/download, company context, logs, metrics, and tool loading work end to end.
Bring up the full Centaur development stack locally with cargo-run Rust API, Kind agent sandboxes, onepassword/iron-proxy credentials, Tailscale Funnel Slack webhooks, Slack app manifest setup, and centaur-session-cli smoke tests or thread attachment.
Run a focused Centaur tool health smoke test across every live tool CLI. Use when asked to smoke test tools, check all tool auth/connectivity, validate brokered credential injection, or produce a Slack-ready health report for the current deployment.
AGENTS.md instructions for paradigmxyz/centaur, covering centaur agent guide, scope and instruction hierarchy, how to work here, architecture boundaries and local development and validation.