laurigates

Adversarial second-pass review that tries to break code, designs, plans, or ADRs. Use when stakes are high and a normal review already ran.

Configure Claude Code agent teams (implicit team, SendMessage, TaskUpdate). Use when running parallel agents, coordinating with messaging, or setting up a lead/teammate architecture.

Gate outward-bound text (upstream issues, docs, PR bodies) through isolated haiku fresh-reader critique before publishing. Use when an artifact must survive a reader with zero project context.

Write and configure custom agent definitions in Claude Code agents/ directory. Use when creating an agent .md file, defining a specialized agent, or configuring agent tools.

Pre-dump-then-dispatch for tools holding an exclusive lock (Ghidra, migrations, single-writer caches). Use when fanning out parallel agents needing a non-concurrent resource.

Execution-grounded review: run tests first, trace each acceptance criterion to execution evidence. Use when verifying an implementation meets spec.

Copy, generalize, or merge a project's .claude/{agents,commands} into user-scoped configuration. Use when assimilating another project's Claude setup or generalizing an agent.

Audit Claude subagent configs for completeness, security, and best practices. Use when reviewing agents/ for missing frontmatter, overprivileged tools, or bad model choices.

Comprehensive USB camera and UVC device analysis for debugging video streaming issues. Use when diagnosing camera connectivity, format negotiation, or control capabilities.

Audit Android app layouts for Material Design 3 compliance, accessibility, edge-to-edge support, and modern best practices. Use for layout reviews, pre-release checks, or establishing baseline quality.

AST-based code search using ast-grep for structural pattern matching. Use when searching for code patterns, refactoring, or performing semantic code analysis across multiple languages.

Code coverage for Rust using LLVM instrumentation with support for multiple output formats and CI integration. Use when measuring test coverage, generating coverage reports, enforcing coverage thresholds, or integrating with codecov/coveralls. Trigger terms: coverage, llvm-cov, code coverage, test coverage, coverage report, codecov, coveralls, branch coverage.

Detect unused dependencies in Rust projects for cleaner Cargo.toml files and faster builds. Use when auditing dependencies, optimizing build times, cleaning up Cargo.toml, or detecting bloat. Trigger terms: unused dependencies, cargo-machete, dependency audit, dependency cleanup, bloat detection, cargo-udeps.

Next-generation test runner for Rust with parallel execution, advanced filtering, and CI integration. Use when running tests, configuring test execution, setting up CI pipelines, or optimizing test performance. Trigger terms: nextest, test runner, parallel tests, test filtering, test performance, flaky tests, CI testing.

Advanced Clippy configuration for comprehensive Rust linting with custom rules, categories, and IDE integration. Use when configuring linting rules, enforcing code standards, setting up CI linting, or customizing clippy behavior. Trigger terms: clippy, linting, code quality, clippy.toml, pedantic, nursery, restriction, lint configuration, code standards.

Analyze codebases for anti-patterns, code smells, and quality issues using ast-grep structural pattern matching. Use when reviewing code quality, identifying technical debt, or performing comprehensive code analysis across JavaScript, TypeScript, Python, Vue, React, or other supported languages.

Generate a printable Typst build guide (source + PDF) for an ESP32/MCU project by analyzing its docs, source, and schematic

Register a project in the monorepo — justfile mod, CI matrix, standard file inventory

Standardize credential handling for an ESP32 project (credentials.h.example, .gitignore, pre-commit protection)

Set up ESP-IDF development environment, create new projects, and verify configuration

Generate a CLAUDE.md for a project with build commands, hardware constraints, architecture, and development tasks

Audit project completeness against the monorepo standard checklist (docs, config, registration)

Generate a standardized README.md for an ESP32 project by analyzing source code, justfile, and hardware configuration

Audit sdkconfig.defaults by inferring needed settings from source code analysis

Send notifications, interactive questions, or multiple-choice polls to the user via Telegram. Use when the user asks to be notified ("ping me", "notify me on Telegram", "ask me when..."), when a long-running task finishes and the user is likely away, when an irreversible action needs out-of-band confirmation, or when the user should pick among several fixed options ("ask me which one via poll"). Provides telegram-notify (one-way), telegram-ask (send + block for reply), and telegram-poll (send a multiple-choice poll + block for the vote).

Modern Neovim configuration expertise including Lua scripting, plugin management with lazy.nvim, LSP setup with Mason, AI integration with claudecode.nvim/opencode.nvim, and workflow optimization. Covers keymaps, autocommands, and treesitter configuration. Use when user mentions Neovim, nvim, lazy.nvim, Mason, init.lua, Lua config, nvim plugins, or Neovim customization.

Draft bite-sized "AI as coworker" wins, experiences, and useful failures for sharing on Google Chat. Use when the user says "draft a shareable about X", "share this win", "add a shareable", "make the technical/layman/one-liner/takeaway version of X", or "format the <topic> <register> for posting". Drafts each topic in four registers (layman, technical, one-liner, takeaway), queues them in FVH/shareables.md, and hands off a clipboard-ready Google Chat message to paste.

Scan all git repositories under ~/repos and report recent activity — last commit age, branch, uncommitted changes — in age-bucketed tables. Use when the user asks for a repo activity overview, "what have I been working on", portfolio status, or which repos are active/dormant.

Comprehensive chezmoi dotfiles management expertise including templates, cross-platform configuration, file naming conventions, and troubleshooting. Covers source directory management, reproducible environment setup, and chezmoi templating with Go templates. Use when user mentions chezmoi, dotfiles, cross-platform config, chezmoi apply, chezmoi diff, .chezmoidata, or managing configuration files across machines.

Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.

Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.

Obsidian Bases database feature for YAML-based interactive note views. Use when creating .base files, writing filter queries, building formulas, configuring table/card views, or working with Obsidian properties and frontmatter databases.