Kastalien-Research/thoughtbox

Kastalien-Research/thoughtbox

Agent Claude Code

Explore a subsystem or module and produce Mermaid architecture diagrams documenting data flows, component relationships, and system context.

Kastalien-Research/thoughtbox

Agent Claude Code

Proactively audit the assumption registry for stale, unverified, or newly-broken assumptions. Use on a schedule (weekly) or when starting work that depends on external systems. Unlike dependency-verifier (reactive, investigates on demand), this agent walks the full registry and flags what needs attention.

Kastalien-Research/thoughtbox

Agent Claude Code

Maintain awareness of all active workstreams, prevent conflicts between parallel tasks, and ensure unblocked work continues moving. Use for status checks, dependency analysis, task reordering, and detecting conflicts between parallel workstreams.

Kastalien-Research/thoughtbox

Agent Claude Code

Track aggregate token spend and API costs across all agent operations. Enforce budget constraints, detect cost anomalies, and recommend budget reallocation. Use for daily cost rollups, budget enforcement, and spend optimization.

Kastalien-Research/thoughtbox

Agent Claude Code

Verify that external dependencies, APIs, specs, and tools actually behave as documented. Use when you need to validate assumptions about external systems, check if a spec is actually implemented, or investigate ecosystem adoption of a feature. This agent tests against real-world implementations, not just documentation.

Kastalien-Research/thoughtbox

Agent Claude Code

Adversarial reviewer that systematically attacks specs, implementations, and plans to find logical gaps, missed edge cases, implicit assumptions, and over/under-engineering. Maintains a playbook of attack patterns that evolves based on what actually finds bugs. Use on any artifact you want stress-tested before…