(no description)
Review AI-generated or human-written code changes with fallow's graph-grounded review brief. Subtracts deterministic concerns (unused code, complexity, duplication, styling) from the loop, ranks what to look at by blast radius and risk, and surfaces the few consequential structural decisions (new public-API contracts, coupling/boundary crossings, new dependencies) as framed judgment questions anchored to verifiable signals. Drives a closed agent-contract loop: fetch the walkthrough guide, return a judgment, and have fallow post-validate it against the live graph (hallucinated or stale judgments are rejected). Use when asked to review a PR, review a branch, review a diff, do a code review, or check changed code before merge.
Codebase intelligence for TypeScript and JavaScript. Static analysis of code and styles reports changed-code risk, cleanup opportunities, duplication, circular dependencies, complexity hotspots, architecture boundaries, design-system drift, feature flags, and opt-in security candidates. Runtime coverage can merge production execution data for hot-path review, cold-path deletion confidence, and stale-flag evidence. 123 framework plugins, zero configuration, sub-second static analysis. Use when asked to audit PR risk, find unused code or dependencies, detect duplicates, check styling consistency, inspect architecture boundaries, merge runtime coverage, auto-fix supported issues, or run fallow.
Writes and reviews semantic, accessible HTML and template markup that stays readable and low-noise. Use when creating or refactoring HTML or Svelte templates, cleaning up div soup, choosing better elements, improving form markup, fixing heading or landmark structure, or replacing custom controls with native HTML.
Generates project READMEs with two variants: a generic open-source template and a specialized 42 School project template. Use when the user asks to generate, update, or create a README file.
Deep web research using parallel sub-agents. Classifies question into depth tier (quick/standard/deep), spawns proportional researcher sub-agents, synthesizes into short answer + detailed report with citations. Use when user asks "best X for Y", "compare A vs B", "what is best approach for Z", "research X", "how does X compare to Y", or needs deep investigation.
Execute a planned workflow autonomously without stopping to explain steps. Halts only for manual testing, missing information, or major ambiguity. Use when user wants to start deep work, run autonomously, or execute a plan without interruptions.
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.