Agent skill · software engineering · fallow-rs
fallow-review
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.
Why this skill is useful
Adds a comprehensive executable script for graph-grounded code review that integrates with existing version control systems and enhances review processes.
What it needs
Requires fallow installed locally. About 11k tokens when loaded. Last updated 2026-08-04. 111 stars on the source repository.
What this skill does
Fallow Review: graph-grounded code review fallow review turns a changeset into a deterministic, graph-derived review brief and an agent-contract loop. It answers "where do I look, and what calls actually need human taste?" rather than "will CI block this?" (that is fallow audit, which gates). review always exits 0, so it is safe to run regardless of verdict. The four jobs it does, in order: subtract: dead code, complexity, duplication, and styling for the changed files are reported and kept OUT of the judgment loop, so attention is not spent on what a deterministic check already owns. focus: changed-file units are ranked by a composite attention score (fan-in/out, risk zone, change shape) with a review-here / not-prioritized label and a full deprioritized escape-hatch list, so nothing is hidden. structure: the decision surface lifts the handful of consequential STRUCTURAL decisions out of the diff and frames each as a judgment question, capped to a working-memory-sized set, each anchored to a signalid fallow emitted. direct: the walkthrough guide hands an agent a graph-derived digest, the review direction, a graph-snapshot pin, and the exact judgment schema to return. When to use Reviewing a PR, branch, or diff (AI-generated or human-written) before merge. After an agent has done work and removed the fallow findings it could; this surfaces what is left for human/agent taste. Producing inline-reviewable judgments that can flow back to the agent that wrote the code. When NOT to use Gating CI on a pass/fail verdict: use fallow audit (it exits non-zero on a fail verdict). Whole-project health, cleanup, or dead-code reports: use the fallow skill. Quick human brief The human brief prints the orientation facts, the focus map, and the decision surface ("Decisions to make"). --format json emits the full structured envelope (decisions, focus, deltas, impactclosure, partition, graphfacts). --max-decisions N tunes the cap (clamped to a small band). …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills fallow-rs/fallow-review