A workflow operating system for AI-assisted engineering. Task state, decisions, and plans live on disk as files, not in chat history, so context survives across sessions, tools, and restarts.
This repository also configures its own agents. See what fhorja.dev tells them →
Command Claude Code
Generate an outward-facing delivery artifact (executive summary, slack or email update, demo script, release note, blog post draft) from the current task's work, scoped per audience and per format. Persists as DELIVERYASSET .md inside the active task folder. Distinct from pr-package (GitHub-scoped) and team-update…
Command Claude Code
Bootstrap a design system from a Figma file using MCP tools. Extracts token variables, identifies components, creates the directory structure, and generates scaffolded foundation docs and a component inventory. Use when starting a new project with a Figma design file. Do not use when the design system docs already…
Command Claude Code
Review a component or screen implementation against its spec doc for alignment on variants, states, accessibility, tokens, and visual fidelity. Distinct from review-hard (general risk) and repo-consistency-sweep (pattern matching). Activates when a slice's declared Scope touches a design-system button, icon, or…
Command Claude Code
Capture a small-to-medium course correction the user realized mid-task (not from external review), record it as a numbered D-N entry in DECISIONS.md, update TASKSTATE.md to reflect the adjusted direction, and route back to the appropriate command. Use when you are mid-task (any phase past discovery) and realize the…
Command Claude Code
Orchestrator-workers variant of external-research for multi-modal sweep across distinct angles or source-groups of one research question. Promotes external-research's inline delegation to a first-class orchestrator with a worker contract and provenance. Sonnet orchestrator dispatches N Sonnet workers (one angle each)…
Command Claude Code needs its repo
Synthesize multiple external sources into a task-scoped EXTERNALRESEARCH.md grounded in REFERENCES.md entries. Each source is captured first via capture-references (project-level memory; deduplicated by URL); this command produces the synthesis with comparative analysis and a model recommendation visually separated…
Command Claude Code
Extract canonical foundations docs (foundations/color.md, foundations/typography.md, foundations/spacing.md, foundations/radii.md) from a batch of existing SCREENSPECs. Idempotent: re-runs only add new tokens, never overwrite existing role mappings, and route conflicts to a Review queue. Use when SCREENSPECs already…
Command Claude Code
Orchestrator-workers variant of feature-library-scout for deep per-feature-problem library research. The orchestrator derives the feature-problem list and dispatches one Sonnet worker per problem; each worker ranks candidate libraries by adoption signal (registry downloads, dependents, last release, stars and trend…
Command Claude Code
Research and recommend community-vetted best-in-class libraries for each feature problem in the product (lists, camera, forms, keyboard, sheets), ranked by adoption signal (downloads, dependents, recency, stars-trend, maintenance, platform fit) relative to the project's ecosystem. Stack-agnostic across registries…
Command Claude Code
Compare design tokens in code against foundation docs and optionally Figma variables to detect drift (tokens added without documentation, documented tokens not in code, value mismatches). Use when the design system has been evolving and you want to verify foundations are in sync. Do not use when no foundation docs…
Command Claude Code
Review a frontend architecture at scale and gate micro-frontend adoption BEFORE building. The first step is an adopt-or-don't-adopt decision (default: you probably do not need micro-frontends; prefer a modular monolith until 3 or more independently deploying teams and real coordination pain exist), then a checklist…
Command Claude Code
Produce a staff-grade frontend system-design RFC for the active task: a 12-section design document (problem, requirements, architecture, data model, API and interface contract, rendering and delivery, state management, performance budget, accessibility, security, rollout, trade-offs) covering web and mobile, persisted…
Command Claude Code
Verify a built Godot 2D or 3D scene at runtime: run the scene (press-play or headless), read the captured debugger output, classify any runtime errors against a Godot-specific taxonomy, and decide a PASS/FAIL runtime gate for the slice's acceptance behavior. The run's real output IS the Layer-1 runtime evidence…
Command Claude Code
Plan the Godot scene and node structure for a 2D or 3D game feature before any GDScript is written: the scene tree, node types and responsibilities, autoloads (singletons), signal wiring, the input map, and the resources and sub-scenes to create. Produces GODOTSCENEPLAN.md, a design-time plan an MCP-driven editor or a…
Command Claude Code
Review a GraphQL schema and a Backend-for-Frontend (BFF) contract BEFORE implementation, against a GraphQL-specific checklist: schema shape and nullability (null-bubbling), errors-as-data unions, N+1 and DataLoader, query cost and depth limits, cursor-connection pagination, federation entity ownership, breaking-change…
Command Claude Code
Scan the current working session and the active task's artifacts for reusable, generalizable lessons (what was tried, what failed and why, what surprised us, what the next task should do differently) and propose anchored entries to append to the task's LEARNINGS.md, the produce-side counterpart to the ADR-0017 consume…
Command Claude Code
Break the task out of a loop, confusion state, or false-progress state, and determine the fastest safe path forward. Diagnoses whether the issue is technical, workflow-related, or scope-related, then routes to the right recovery command and editor mode (Ask by default; Debug if the stuckness is a concrete technical…
Command Claude Code
Generate a design-system spec from a raw image file (a screenshot, mockup, or captured app screen) when there is no Figma source. Reads the image with vision and emits a COMPONENTSPEC.md-shaped doc (--component) or a SCREENSPEC.md-shaped doc (--screen), auto-detecting the mode when no flag is given. A gated --gameplay…
Command Claude Code
Understand the requested change deeply enough to make safe workflow decisions, then persist the analysis as IMPACTANALYSIS.md in the active task folder. Per-repo subsections when multi-repo. Identifies blast radius, contract impacts, schema/runtime risks, and integration points before planning or coding. Use when a…
Command Claude Code
Implement only the approved slice with minimal, explicit, review-friendly changes, then persist execution evidence in slice notes and TASKSTATE.md. The single official execution path of the workflow. Supports an opt-in test-first (TDD) mode, enabled per slice or via --tdd, that writes the failing test before the code…
Command Claude Code
Orchestrator-workers variant of implement-approved-slice that executes independent approved slices in parallel. Reads per-slice Scope and Depends-on from IMPLEMENTATIONPLAN.md, builds the slice DAG, computes parallelizable waves (ready slices whose file scopes are pairwise disjoint with no shared migration, lockfile…
Command Claude Code
Execute a bounded micro-delta (adjustments, fixes, polish, missed checklist items) that stays inside the same slice intent and DECISIONS.md, then record evidence in slice notes and/or TASKSTATE.md without churning unrelated artifacts. Use when a slice was already implemented or is ready-to-close-with-follow-ups and…
Command Claude Code
Define an incremental, reviewable, production-safe implementation plan for the active task and persist it as IMPLEMENTATIONPLAN.md plus a TASKSTATE.md update. Breaks work into the smallest safe slices with objective, exact scope, ordering rationale, key risks, validation approach, exit criteria, and work complexity…
Command Claude Code
Triage a concrete observed technical failure (stack trace, error, failing test, runtime symptom, production alert), classify the failure type (REGRESSION/NEWBUG/CONFIG/EXTERNALDEPENDENCY/REPRODUCIBILITY/DIAGNOSTICINSUFFICIENT), recommend fix size (HOTFIX/SLICE/INVESTIGATION/ESCALATE), and validate against locked…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: