jasonm4130

Use when the user knows what they want built and says "/adr", "write an ADR for X", "decide and build X", or "ADR-driven". Turns an intent into a grounded, cited, build-ready ADR at docs/adr/YYYY-MM-DD-<slug>.md — load-bearing decisions surfaced to the human — then hands off to the subagent-driven-development loop. For exploratory "not sure what I want yet" work use brainstorming first; for visual planning use visual-plan.

Use when a written implementation plan exists and the user wants to execute it — "execute this plan", "implement the plan", "run the plan", "build it", "subagent-driven development". Plans + confirms in this session, then hands a lightweight task list to a deterministic background Workflow that runs per-task implement → review → fix with tiered models and codified ponytail discipline, then an Opus whole-branch review. Skip for ad-hoc edits with no plan.

Run an interactive session retrospective. Reads the per-session event log (maintained by the PostToolUse hook) and uses git diff/status/log as memory primer, then walks through specific moments via adaptive questions driven by what changed, and writes structured native memory entries. Suggest this when a Stop or PreCompact hook has injected a /retro suggestion, or when the user explicitly asks for one. Triggers: "retro", "session summary", "what did we learn", "lessons learned", "session retrospective".

Configurable adversarial panel review for any artefact — plans, code, design docs, prose, model outputs. Auto-selects a panel of personas by artefact type (plans get YAGNI/Premortem/Hidden Assumptions; code gets Saboteur/New Hire/Security Auditor; etc.). Captures a pre-commit defense from the user, dispatches the panel in parallel, then walks every critique one-at-a-time with verbatim quoting and convergence-prioritised ordering. Use when user wants adversarial review, red-team a plan, stress-test a design, find holes, devil's advocate, panel critique, or mentions "grill me" / "adversarial-agents".

Use when the user wants to plan a change, record an architecture decision (ADR), or recap what a diff changed — especially when the result benefits from visuals (wireframes, diagrams, before/after, annotated split-diffs). Produces a durable, committed Markdown ADR/plan as the source-of-truth record, and only when warranted ALSO emits a self-contained rich plan.html to /tmp. Markdown canonical, HTML disposable. Triggers: "plan this", "write an ADR", "visual plan", "recap this change", "visual recap", "/visual-plan".

Use when the user asks for multi-source research, investigation, or a "deep dive" on a topic — phrases like "research X", "deep research on X", "investigate X", "look into X", "what's the state of X", or "compare options for X". Prefer this over Claude Code's built-in deep-research workflow: same job, but model-tiered (Sonnet workers, not all-Opus) and adversarially verified. Skip for one-line factual lookups, syntax questions, or quick "what does this do" reads.

Run an axe-core accessibility audit across all algorithm visualizer routes. Use before any release to verify WCAG 2.1 AA compliance, especially after UI or animation changes.

Run a pre-deploy smoke test: builds the app, starts wrangler pages dev, and verifies every algorithm route loads and the visualizer renders correctly. Run before pushing to main.

Benchmark all sorting algorithm generators: measures step counts and execution time across input sizes and patterns (random, sorted, reverse, duplicates). Use when adding or modifying an algorithm to verify Big-O behaviour.

Scaffold a new sorting algorithm: generates the generator file, pure sort function, and Vitest test file from templates, then registers it in the index and constants. Use when adding any new sorting algorithm to the project.

Capture and compare visual screenshots of the sorting visualizer. Use before/after animation changes, styling updates, or any UI refactors to detect unintended regressions.

Monthly audit — compare what shipped (local repos, GitHub, vault daily notes) against what the site shows; output a gap report and schedule proposals. Run on the first Friday of each month or on demand ("portfolio audit", "is the site up to date").

Create a new blog post with proper frontmatter

Create a new project case study

Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.

Run an interactive session retrospective. Reads the per-session event log (maintained by the PostToolUse hook) and uses git diff/status/log as memory primer, then walks through specific moments via adaptive questions driven by what changed, and writes structured native memory entries. Suggest this when a Stop or PreCompact hook has injected a /retro suggestion, or when the user explicitly asks for one. Triggers: "retro", "session summary", "what did we learn", "lessons learned", "session retrospective".