Is the Fallow Review skill free?

Yes. The skill itself is free from fallow-rs/fallow-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Fallow Review SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Fallow Review?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Fallow Review with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Fallow Review

Turns a diff into a ranked, graph-validated review brief with an anti-hallucination judgment loop.

by fallow-rs · fallow-rs/fallow-skills

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.4/10
Tested: Jul 13, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 0f57acd

On a synthetic 4-file TS diff (new public export, a new payments-to-analytics import, a new npm dependency), the skill's subtract/focus/structure framing surfaced the cross-zone coupling risk and a breaking return-shape change that a plain ad-hoc review missed entirely — but its headline feature, graph-validated signal IDs that reject hallucinated judgments, needs the separate `fallow` CLI installed and was not exercised in this run.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 4/5

What Fallow Review does

Fallow Review structures code review around a live dependency graph: it ranks changed files by blast radius, subtracts deterministic noise (dead code, duplication, styling) from the loop, and lifts new public-API contracts, cross-boundary coupling, and new dependencies into framed judgment questions anchored to graph signal IDs. Trigger it by asking to review a PR, branch, or diff, or to check changed code before merge; the graph-validated agent-contract loop requires the separate `fallow` CLI (npm/cargo install) to actually run.

How to install Fallow Review

git clone https://github.com/fallow-rs/fallow-skills
cd fallow-skills
mkdir -p ~/.claude/skills
cp -r fallow/skills/fallow-review ~/.claude/skills/fallow-review

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Fallow Review

/fallow-review Turns a diff into a ranked, graph-validated review brief with an anti-hallucination judgment loop.

It also activates on plain-language prompts like these:

Review this pull request diff before I merge it
Rank the changed files in my branch by blast radius
Check my diff for cross-module coupling risks

Frequently asked questions

Is the Fallow Review skill free?: Yes. The skill itself is free from fallow-rs/fallow-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Fallow Review work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Works with setup. On a synthetic 4-file TS diff (new public export, a new payments-to-analytics import, a new npm dependency), the skill's subtract/focus/structure framing surfaced the cross-zone coupling risk and a breaking return-shape change that a plain ad-hoc review missed entirely — but its headline feature, graph-validated signal IDs that reject hallucinated judgments, needs the separate `fallow` CLI installed and was not exercised in this run.
What is the Fallow Review SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Fallow Review?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Fallow Review with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.