fbosch

Guidance for Worktrunk (the `wt` CLI) — git worktree management, hooks, and config. Load when editing .config/wt.toml or ~/.config/worktrunk/config.toml; adding, modifying, or debugging hooks (post-merge, post-start, pre-commit, pre-merge, post-switch, etc.); configuring commit message generation or command aliases; or troubleshooting wt behavior. Also answers general worktrunk/wt questions.

Use when a repository contains a `justfile` or `.justfile` and work should flow through `just` recipes instead of ad-hoc shell commands. Covers recipe discovery, execution, debugging, and concise recipe authoring/refactoring for repeatable project tasks.

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.

Offer optional 10-15 minute deliberate learning exercises during AI-assisted coding. Use when the user asks for a learning opportunity, deliberate practice, retrieval check-in, prediction exercise, teach-back, or when substantial work created a good moment to offer learning. Do not use for ordinary implementation unless the user explicitly wants learning.

Write effective pull request description bodies that explain what changed, why it changed, reviewer focus, validation, and risk. Use when creating, reviewing, or improving PR descriptions for internal work, OSS contributions, infra changes, migrations, or WIP requests for early feedback.

Write and edit substantial human-facing prose with clear, concise technical style while preserving the user's canonical voice from `~/.config/opencode/TONE.md`. Use for documentation, README prose, PR descriptions, commit-message bodies, changelog notes, issue summaries, long-form explanations, UI/help text, error messages, and copyediting drafts for clarity, concision, structure, tone, and tradeoffs.

Audit and safely clean low-value, redundant, misleading, flaky, over-mocked, or AI-generated unit tests. Use when asked to clean useless tests, prune test suites, remove redundant tests, audit low-value tests, improve test signal, clean brittle snapshots, reduce test noise, review coverage theater, or decide whether tests should be kept, rewritten, consolidated, moved, quarantined, or deleted.

Use when creating, editing, reviewing, or troubleshooting devenv.sh developer environments, including devenv.nix, devenv.yaml, packages, languages, services, tasks, scripts, processes, tests, GitHub Actions, containers, MCP/LSP integration, or reproducible Nix-based project setup. Also use when an agent needs to discover devenv options/packages, validate environment changes with devenv test, or decide between tasks/scripts/processes/services.

Create new NixOS, Darwin, or Home Manager modules following the dendritic flake pattern. Use when the user wants to add a new feature module (service, program, system configuration, etc.) to their flake. Triggers include requests like "add [feature] module", "create a module for [feature]", "set up [feature] in the flake", or "add nginx/git/firefox/etc."

Debug failing NixOS builds and activations. Use when build fails (infinite recursion, attribute errors, evaluation errors), activation fails (systemd services, SOPS secrets, home-manager), or when asking to "debug build", "fix activation error", "why is rebuild failing", or "troubleshoot NixOS issue". Handles SOPS decryption issues, systemd service failures, and common NixOS configuration errors.

Package software into reproducible Nix derivations for local flakes and nixpkgs contributions. Use when creating or updating package expressions, debugging build/install/runtime failures, resolving source hash mismatches, selecting native language builders (buildGoModule, buildRustPackage, buildPythonPackage, buildNpmPackage, bundlerApp, zig.hook), or deciding when helper generators are justified.

Run janitorial cleanup for this flake with dendritic-aware linting. Use when preparing to commit, when CI fails on lint errors, or when user asks to "clean up code", "run lints", "fix warnings", or "check flake". Handles statix/deadnix with proper exclusions and resolves conflicts with dendritic pattern.

Validate dendritic Nix flake pattern usage in this repository. Use when reviewing modules, refactoring code, or checking dendritic pattern compliance. Validates flake-parts module structure, aspect-oriented design, feature organization, and adherence to dendritic principles from the Doc-Steve/dendritic-design-with-flake-parts wiki.

Run Impeccable-backed UI design reviews for this app. Use when auditing visual design, UX polish, responsive quality, AI-slop anti-patterns, hierarchy, spacing, typography, color, motion, or when the user asks for Impeccable, design audit, design critique, design backlog, polish, bolder, quieter, layout, typeset, colorize, or harden passes.

Enforce high-risk accessibility invariants for interactive React UI. Use when implementing/refactoring clickable wrappers, icon-only controls, sortable tables, dialogs, keyboard flows, or live status updates.

Apply repository Zod boundary-validation conventions with consistent error shapes. Use when changing API handlers, loaders, localStorage/persistence flows, import/export parsers, or legacy payload migrations.

Prevent React derived-state regressions and effect-sync loops. Use when editing `useState`/`useEffect`/selectors, adding filtering/sorting/formatting logic, or debugging stale UI caused by duplicated state.

Codebase intelligence for JavaScript and TypeScript. Free static layer reports quality, changed-code risk, cleanup opportunities (unused files, exports, types, dependencies), code duplication, circular dependencies, complexity hotspots, architecture boundary violations, feature flag patterns, and opt-in security candidates. Runtime coverage merges production execution data into the same health report for hot-path review, cold-path deletion confidence, and stale-flag evidence, with a single local capture available by default and continuous/cloud runtime monitoring available as an optional mode. 122 framework plugins, zero configuration, sub-second static analysis. Use when asked to analyze code health, audit PR risk, find cleanup opportunities or unused code, detect duplicates, check circular dependencies, audit complexity, check architecture boundaries, detect feature flags, surface security candidates, clean up the codebase, auto-fix issues, merge runtime coverage, or run fallow.

Use when building, running, testing, or bundling JavaScript/TypeScript applications. Reach for Bun when you need to execute scripts, manage dependencies, run tests, bundle code for production, or build HTTP servers with native performance.