Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/vuki656/review.nvim/claude-mdgit clone --depth 1 https://github.com/vuki656/review.nvimWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/vuki656/review.nvim/claude-md)<a href="https://agentmods.dev/instructions/vuki656/review.nvim/claude-md"><img src="https://agentmods.dev/badge/instructions/vuki656/review.nvim/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.03291 | $0.03291 |
| Opus 5 | $0.01646 | $0.01646 |
| Sonnet 5 | $0.00658 | $0.00658 |
| Haiku 4.5 | $0.00329 | $0.00329 |
Grade A, and why
review.nvim CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Overview
review.nvim is a Neovim plugin for reviewing AI-generated code changes. :Review opens a dedicated tab of floating windows: a sidebar of stacked floats (Branch, Files, Branches, Commits, Comments — configurable via ui.panels, though Files cannot be disabled) on the left and a diff pane on the right. It browses git diffs, attaches typed comments to lines, and exports review feedback to the clipboard or tmux/herdr (designed for Claude Code workflows).
Commands
# Lint
luacheck lua/
# Run all tests
make test
# Run a single test file
make test-file FILE=tests/test_diff.lua
# Format code
stylua lua/
Workflow
After every code change, run luacheck lua/ and make test. Fix ALL luacheck warnings (not just errors) before considering the task done — zero warnings is the target. When adding new features or logic to pure modules (non-UI, non-git-shelling), always add corresponding tests in tests/. If a module is testable (pure logic, no vim.api dependencies), it should have tests.
CI (.github/workflows/ci.yml) runs three jobs: make test on Neovim stable and nightly, luacheck lua/, and stylua --check lua/ (pinned to stylua 2.5.2). Formatting is enforced, so run stylua lua/ before committing or CI fails.
Behavior changes are documented in three places that are expected to stay in sync: README.md, doc/review.txt (vimdoc), and this file.
The plugin targets Neovim 0.10+; plugin/review.lua hard-refuses to load below that.
Testing
Uses mini.test (from mini.nvim). Dependencies are auto-cloned into .deps/ (gitignored) by the Makefile.
Test files live in tests/ and follow the naming convention test_<module>.lua. Each test file requires only the modules it needs — the plugin is not loaded globally.
Shared fixtures and factories are in tests/helpers.lua.
Tested modules: comment_types, config, core/diff, core/format, core/json_persistence, core/paths, core/watcher (only is_ignored_path), export/markdown, quick_comments/init (send), quick_comments/markdown, quick_comments/panel (send keymap), quick_comments/state, state, ui/panel_keymaps. core/git is tested only for its pure parsers (tests/test_git_parse.lua covers name-status and commit-line parsing); everything in it that shells out to git is not.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · +69 tokens per session d384b36b2d06
- 4d ago First seen · 177 lines · 3,222 tokens per session scan A fbbebac8cc33
review.nvim CLAUDE.md is an instructions file published in the GitHub repository vuki656/review.nvim (53 stars, last pushed yesterday), licensed MIT. It adds 3,291 tokens to every session, about $0.0165 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
fff AGENTS.md
AGENTS.md instructions for dmtrKovalenko/fff, covering to clankers, development commands, building, testing and development tools and code quality.
codecompanion-spinners.nvim GEMINI.md
Instructions for lalitmee/codecompanion-spinners.nvim, covering codecompanion spinner - comprehensive context, project overview, architecture, core components and event handling.
fff CLAUDE.md
Claude Code instructions for dmtrKovalenko/fff, a project described as: The fastest and the most accurate file search SDK for AI agents, Neovim, Rust, C, Python, Bun and NodeJS.
agentic.nvim AGENTS.md
Instructions for carlos-algms/agentic.nvim, covering agents guide, nested instructions, skill driven, domain glossary — lazy read and architectural decisions (adrs) — optional read.
hlchunk.nvim AGENTS.md
Instructions for shellRaining/hlchunk.nvim, covering agents.md, 项目定位, 技术栈约束, 本地命令 and 目录地图.
agentic.nvim CLAUDE.md
Instructions for carlos-algms/agentic.nvim: CRITICAL See @AGENTS.md for Instructions, it's the source of truth for all my instructions, no exceptions, it should be read and be part of your context before any other action.