Invoke ONLY when explicitly asked for a deep, evidence-based investigation of how Caracal works, where something lives, why it behaves a certain way, or whether a concept/feature exists. This is a Caracal-specific researcher that investigates code, docs, configs, tests, and architecture together to answer with…
Invoke ONLY when explicitly asked for an outside-in usability and adoption assessment of Caracal from a real external engineer's perspective. This agent evaluates: Console UX, SDK ergonomics, CLI experience, documentation clarity, deployment workflows, provider/gateway setup, policy model, app/resource modeling…
Invoke ONLY when explicitly asked for a production-readiness audit or hardening of the Caracal OSS platform: reliability, stability, recoverability, scalability, observability, performance, operational simplicity, deployment, upgrade safety, and maintainability. Finds production gaps, explains root causes, designs…
Use this agent when you need to prepare, validate, and publish a production release for a software project. This agent is designed for release engineering tasks including: preparing a new version release (e.g., 'Cut release v0.2.0 or v0.2.0-rc.1'), validating release readiness across all dimensions (code, packages…
Invoke ONLY when an explicit, security-focused review of Caracal is requested. This agent performs deep security audits of code, platform architecture, operations, and product design across all Caracal components including Console, SDK, CLI, APIs, runtime, delegation, grants, providers, resources, applications, zones…
Invoke ONLY when explicitly asked for a production-readiness audit or hardening of the Caracal OSS platform: reliability, stability, recoverability, scalability, observability, performance, operational simplicity, deployment, upgrade safety, and maintainability. Finds production gaps, explains root causes, designs…
Use when changing Caracal commands, package scripts, the web console, runtime CLI launchers, command catalogs, completions, or command documentation. Enforces the runtime-script versus product-management boundary.
Use when writing, editing, or reviewing web console help, info pages, field examples, guided setup copy, or example-facing web console UI text. Enforces the approved Caracal demo naming universe.
Use when writing, editing, or reviewing Caracal documentation under caracal/docs/. Enforces production-grade technical writing, page-flow awareness, and scoped coherent docs edits.
Use when updating infrastructure, dependencies, runtimes, build tooling, or platform-facing code in caracal or caracalEnterprise. Enforces latest stable versions and OS-, framework-, and environment-agnostic design through strict abstraction layers and standardized interfaces.
Use when refactoring, cleaning up, or reviewing code for legacy patterns, deprecated structures, fallback paths, backward compatibility layers, or duplicate logic.
Use when working in caracal or caracalEnterprise. Enforces strict isolation between the open-source and enterprise codebases, including imports, dependencies, shared logic, and license boundaries.
Use when adding, changing, or reviewing code in the multi-language client packages (sdk, admin, core, identity, oauth, revocation, verify, adapters, backends). Enforces functional capability parity across TypeScript, Python, and Go.
An empty agent settings file, from a project described as: 🐾 Authority, not credentials, for AI agents: policy-approved actions, delegation that can only narrow, instant revocation, tamper-evident audit.
205 yesterdayA
tokens not measured
copy · 100%Apache-2.0