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 →
Skill Claude Code
Senior Supabase RLS+Auth Boundary Auditor for tenant isolation gaps in migrations and policy DDL BEFORE deploy. Activates when DECISIONS.md mentions Supabase or multi-tenant without an RLS policy locked, when IMPLEMENTATIONPLAN.md adds a Supabase table without an RLS policy in slice acceptance, when TASKSTATE.md ##…
Skill Claude Code
Orchestrator-workers variant of screen-spec. Dispatches N Sonnet workers (1 screen each) in parallel to generate per-screen spec docs from Figma frames, then merges SCREENMAP.md and routes.md from per-worker partials. Use when screen count >= 6 AND Figma MCP is available AND foundations + SCREENMAP exist. Do not use…
Skill Claude Code
Generate a screen specification from a Figma frame using MCP tools (getdesigncontext, getscreenshot). Produces a spec doc matching the SCREENSPEC.md template with layout sketch, components used, spacing observed, data dependencies, copy, accessibility notes, interactions, and error states. Use when documenting a…
Skill Claude Code
Dedicated security review of the current task changes covering threat modeling, OWASP ASVS L1 checklist pass, auth/authz flow tracing, and dependency/secret scanning reminders. Distinct from review-hard (general risk) and repo-consistency-sweep (pattern matching). Activates when DECISIONS.md, IMPLEMENTATIONPLAN.md, or…
Skill Claude Code
Take a draft artifact (IMPLEMENTATIONPLAN.md, SLICES/.md, or PRPACKAGE.md), run a structured critique against a locked per-artifact-type rubric, and produce a revised draft. Evaluator-optimizer pattern per ADR-0021. PROPOSED-by-default in Plan mode; user reviews critique AND revision before APPLIED. Distinct from…
Skill Claude Code
Read-only safety inspection of a third-party agent skill or plugin BEFORE it is installed or trusted. Reads every file in the candidate directory (SKILL.md plus auxiliary and test files, not just the body), compares declared behavior against what the files actually do, scans for exfiltration, secret access, config or…
Skill Claude Code
Decide whether the current slice is ready to close, distinguishing slice completion from full task completion, then persist the result in slice notes and TASKSTATE.md as explicit reviewable closure notes. For single-slice tasks may route directly to delivery. Returns no-op when slice memory would not materially…
Skill Claude Code
Senior reliability engineer defining a service's reliability contract: choose SLIs, set an SLO target and measurement window, compute the error budget (100% minus the SLO), and write the error-budget policy (what happens when the budget is exhausted). Produces SLOSPEC.md. Activates when a service or critical user flow…
Skill Claude Code
Verify that the patterns the model is about to use for a given framework+version are current per official docs, and cache the result as CURRENTPATTERNS.md at the project level. Prevents the "gold-standard audit" anti-pattern where training-data defaults ship outdated patterns (e.g. Supabase getSession when getUser is…
Skill Claude Code
Research and recommend a technology stack for the active project by consulting official documentation, quality articles, and AAA company practices for latest stable versions. Accepts optional user-provided reference links. Produces a STACKRECOMMENDATION.md inside the active task folder with versioned recommendations…
Skill Claude Code
Detect drift between TASKSTATE.md, other task-memory artifacts, and observable reality (code, tests, diff when provided), then propose the minimum set of updates so operational memory is trustworthy again. Use when TASKSTATE.md is stale or internally inconsistent after many edits, IMPLEMENTATIONPLAN.md or SLICES/.md…
Skill Claude Code
Update TASKSTATE.md so it reflects the latest operational truth of the task and can be resumed safely in this or another session. Lighter-weight than state-reconcile (no cross-artifact drift detection); preferred when the update is incremental and trusted. Use when a meaningful planning, decision, implementation, or…
Skill Claude Code
Ask the minimum set of high-value factual questions needed to proceed safely, then persist the result in the task repository. Distinct from decision-interview (factual gaps, not decision-driven gaps). Use when impact analysis or boundary definition revealed missing facts, correctness depends on information that is not…
Skill Claude Code
Perform the terminal task lifecycle transition for a finished task: verify the spec done-conditions, set TASKSTATE.md to its final closed state, and move the task folder from active/ to archive/. The symmetric counterpart to task-init and the only official way to close a whole task. Use when every slice is closed, the…
Skill Claude Code
Orchestrator-workers variant of task-init for decomposing a complex brief into N parallel independent sub-tasks. Orchestrator validates the decomposition (no overlap, clear scope per sub-task, cross-links justified); N Sonnet workers each run a full task-init in parallel producing one task folder with 5 mandatory…
Skill Claude Code
Initialize the official task folder and base task memory inside projects/ /active/YYYY-MM-DD /. Creates README.md, TASKSTATE.md, SOURCEOFTRUTH.md, DECISIONS.md, IMPLEMENTATIONPLAN.md; seeds from PROJECTCHARTER.md when present; emits a multi-repo ## Repositories section in SOURCEOFTRUTH.md when 2+ repos are provided.…
Skill Claude Code
Provision, report, or attach a dedicated git worktree and branch for the active task on a git-backed project, so multiple tasks run in parallel on one repository without colliding on a single working tree. Opt-in and git-gated: a non-git project or an un-opted task is a no-op. Records the worktree path and task branch…
Skill Claude Code
Write a simple, natural English status update for any team channel (Slack, Discord, Teams, email, GitHub PR comment, standup notes), short, grounded, and professional. Channel-portable. Use when the user wants to communicate progress quickly to teammates or reviewers, implementation or planning has reached a…
Skill Claude Code
Define the smallest set of meaningful tests that protects behavior and reduces regression risk for the active task, then persist as TESTSTRATEGY.md plus a TASKSTATE.md update. Avoids forcing a strategy artifact when it adds no material signal. Detects a Godot or Unity target and routes to the matching headless runner…
Skill Claude Code
Plan the Unity GameObject hierarchy and component architecture for a 3D feature before any C# is written: the scene and prefab structure, what each MonoBehaviour owns, the input model, and, for a multiplayer feature, the networked-authority declarations. Produces UNITYSCENEPLAN.md, a design-time plan an MCP-driven…
Skill Claude Code
Orchestrator-workers generalization of verify-against-rubric to N=many artifacts against ONE locked rubric. Dispatches N stateless Sonnet sub-agents in parallel; each receives ONE artifact + the SAME rubric + read-only tools (no TASKSTATE, no DECISIONS, no prior history); returns structured per-criterion verdict.…
Skill Claude Code
Spawn a stateless sub-agent (Claude Code Task tool, Cursor agent mode, or equivalent) with ONLY the artifact path plus the locked rubric plus read-only tools. Sub-agent returns a structured verdict (satisfied, needsrevision, or failed) plus per-criterion feedback. Distinct from self-critique-and-revise (same-context…
Skill Claude Code
Verify a built web or static frontend at runtime: serve the build on an ephemeral free port, assert page identity FIRST (automatic recovery on a collision or stale server), run the web battery (overflow 320 to 2560, keyboard and focus, console errors, Lighthouse and axe when available), and decide a PASS/FAIL/BLOCKED…
Skill Claude Code
Determine the current stage of the active task and recommend the single best immediate next command, editor mode, and work complexity. Routes based on TASKSTATE.md, DECISIONS.md, and IMPLEMENTATIONPLAN.md without reopening broad discovery. Use when the user wants a fast operational answer for what to do next, when the…
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: