Keeps you and your AI agent from building the wrong thing by checking the idea against its users, its key assumptions and cognitive biases before much code gets written. It runs the early product discovery work that teams often skip when building feels faster.
@haabeAccessibility audit, scoped to the surfaces a product actually has. Detects web / rendered_markdown / terminal / native_app /…
@haabeBring Mycelium into a project that already has code. Detects that the repo predates the framework, asks before touching anything,…
@haabeDesign the smallest viable test to validate or invalidate a critical assumption. Based on Torres's assumption testing framework,…
@haabeUse before any research activity or significant decision. Reviews cognitive biases relevant to the current stage.
@haabeUse to evaluate whether current work aligns with Better Value Sooner Safer Happier. Run at diamond completion and periodically.
@haabeLint canvas files for staleness, missing fields, inconsistent evidence types, and orphaned references. Run periodically or before…
@haabeSynchronize canvas state across team sessions via git. Ensures all team members see the same product knowledge.
@haabeUpdate canvas sections with new evidence. Ensures canvas stays current as the single source of truth.
@haabeUse to analyze correction trends, surface recurring patterns, and graduate repeat corrections to guardrails or anti-patterns.
@haabePrint your own north-star row from your own record, and nothing else. Reads .claude/harness/decision-log.md, the canvas and the…
@haabeRender `.claude/canvas/cycle-history.yml` as a Gantt chart + outcome distribution pie (or ascii / json). Read-only. Consults the…
@haabeUse when facing a new problem to classify its domain (Clear, Complicated, Complex, Chaotic, Confused) and select appropriate…
@haabeIs this you? Claim your profilePut a plugin at the top of Plugins, from $9
