kamiazya

kamiazya/whiteboard

Plugin Claude Code

Plugin marketplace listing 1 plugin: whiteboard.

kamiazya/whiteboard

Plugin Claude Code

Collaborative whiteboard for Claude Code. Wraps the @kamiazya/whiteboard-mcp server and exposes the shared skills bundled with that package.

kamiazya/whiteboard

Agent Claude Code

System-design perspective for the plan-initiative panel. Given an initiative + brief, analyzes seams, data model, module boundaries, and trade-offs, and proposes the structural approach. Read-only analysis — does not implement.

kamiazya/whiteboard

Agent Claude Code

Read-only whole-codebase health auditor for ONE dimension (wiring-gaps / architecture / maintainability / contract-drift / test-gaps / dev-experience). Unlike reviewer-dimension (which judges a diff), this audits the repo as it stands for standing problems worth a ticket. Returns evidence-grounded findings with…

kamiazya/whiteboard

Agent Claude Code

TDD implementer for one well-scoped change in the whiteboard repo. Spawned by the dev-loop workflow's Implement phase. Writes the red test first, makes the smallest patch to green, runs the nearest-layer tests + typecheck, and commits only the files it changed. Pass the task, approved design, baseRef, and (optional)…

kamiazya/whiteboard

Agent Claude Code

Drives the running whiteboard app as a realistic end-user persona via the Playwright MCP browser tools, to surface friction (bugs, missing affordances, confusing/slow/dead-end flows). Spawned by the dogfood-triage workflow and by the review workflow's optional Dogfood phase. Pass the persona, goal, app URL, and (for…

kamiazya/whiteboard

Agent Claude Code

Drafts release notes, changelog entries, README hero/positioning, and announcements for the whiteboard project. Release/milestone-time (not in the dev inner loop). Produces DRAFTS only — a human approves before anything is published. Pass the release scope or milestone in the prompt.

kamiazya/whiteboard

Agent Claude Code

Reviews a draft design/plan for one whiteboard dev task BEFORE implementation, against the repo's completeness rubric. Spawned by the dev-loop workflow's PlanReview gate. Returns pass/fail with concrete must-fix items. Does not write code or verify files exist — it judges plan completeness only.

kamiazya/whiteboard

Agent Claude Code

Product/value perspective for the plan-initiative panel. Given an initiative + brief, clarifies user value, scope vs non-scope, success metrics, and deployment variants (SaaS / self-host / standalone). Read-only analysis.

kamiazya/whiteboard

Agent Claude Code

Delivery/sequencing perspective for the plan-initiative panel. Given an initiative + brief, slices the work into coherent units, orders by dependency/risk, and defines milestones and verification gates. Read-only analysis.

kamiazya/whiteboard

Agent Claude Code

QA tester for one specific scenario (startup/docs-reachability/smoke/error-recovery/migration). Spawned by qa to parallelize scenario testing. Pass the scenario name, target branch or worktree path, and any specific files to check in the task prompt.

kamiazya/whiteboard

Agent Claude Code

Lightweight read-only investigator for repo-hygiene / policy / portability questions — e.g. "should we track .claude/ in git", "is it safe to commit this dir", "what breaks for other contributors". Given ONE concern dimension, it inspects the real repo (ignore rules, tracked vs untracked, secrets, machine-specific…

kamiazya/whiteboard

Agent Claude Code

External-research perspective for the plan-initiative panel. Uses web search/fetch to surface industry best practices, prior-art / competitor features, relevant standards, and case studies for the initiative — with cited sources. Read-only; informs the plan, does not implement.

kamiazya/whiteboard

Agent Claude Code

Focused code reviewer for one specific review dimension (contract/boundary/dead-code/test-coverage/auth/correctness). Spawned by reviewer to parallelize multi-dimension review. Pass the dimension and target files/diff in the task prompt.

kamiazya/whiteboard

Agent Claude Code

Threat-modeling / security-design perspective for the plan-initiative panel. Given an initiative + brief, identifies trust boundaries, auth/authz, data exposure, and attack surface at DESIGN time (not diff scanning). Read-only analysis.

kamiazya/whiteboard

Agent Claude Code

Security scanner for one specific attack vector (path-traversal/auth-bypass/CORS/SSRF/info-leak/injection). Spawned by security-reviewer to parallelize security analysis. Pass the vector name and target files in the task prompt.

kamiazya/whiteboard

Agent Claude Code

Behavior-preserving simplification pass over the files a dev task just changed. Spawned by the dev-loop workflow's Simplify phase. Applies the preloaded ponytail ladder (delete > stdlib > native > already-installed > one line) against this repo's disciplines, re-runs the nearest-layer tests, and commits only what it…

kamiazya/whiteboard

Agent Claude Code

Keeps the whiteboard project's developer/user docs in sync with code & behavior changes, and maintains docs IA (Diátaxis). Spawned by the dev-loop Docs phase and invoked ad-hoc for doc gaps. Updates only doc files; commits them separately. Pass the change range/scope in the prompt.

kamiazya/whiteboard

Agent Claude Code

UI/UX perspective for the plan-initiative panel. Given an initiative + brief, analyzes user flows, affordances, information architecture, and states (empty/loading/error/degraded), and proposes the experience. Read-only analysis.

kamiazya/whiteboard

Agent Claude Code

Visualizes a plan/design onto the running local whiteboard via its MCP tools, from abstract concept maps to detailed UI mockups. Spawned by the plan-initiative workflow's Visualize phase. Dogfoods the product while it designs. Pass the plan, canvas target, and depth (concept|detailed).

kamiazya/whiteboard

Hook Claude Code

Runs when a session starts, executing ensure-http-dev-daemon.mjs and stale-issues.mjs via node with --quiet (2 commands). From kamiazya/whiteboard.

kamiazya/whiteboard

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, executing pre-pr-check-base.mjs and pre-pr-visual-evidence.mjs via node (2 commands). From kamiazya/whiteboard.

kamiazya/whiteboard

Hook Claude Code

Runs after a tool call finishes for Bash tool calls, executing post-merge-pull-main.mjs and post-push-pr-sync.mjs via node (2 commands). From kamiazya/whiteboard.

kamiazya/whiteboard

Settings file Claude Code

Agent settings declaring 3 hook events (SessionStart, PreToolUse, PostToolUse).