nvim-buffers

nvim-buffers is a skill for Claude Code, Codex from scott-fryxell/brayness. It costs 94 tokens per session (962 once invoked), scanned A, original, MIT.

A view of the files currently open in Neovim, a keyboard-focused code editor, along with the active editor view. It can also explain your configured Neovim key bindings in context.

In plain words
What is it for?
Use it to review open files, ask about an unnamed file on screen, or learn how to perform an editor action with your Neovim key bindings.
Why use it?
It lets the agent discuss the files and editor state you are actually working with instead of guessing from a file name alone.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review open files, ask about an unnamed file on screen, or learn how to perform an editor action with your Neovim key bindings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/scott-fryxell/brayness/nvim-buffers
Install

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.

Any agent
npx skills add scott-fryxell/brayness --skill nvim-buffers
Clone the repo
git clone --depth 1 https://github.com/scott-fryxell/brayness

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for nvim-buffers

README.md
[![agentmods](https://agentmods.dev/badge/skills/scott-fryxell/brayness/nvim-buffers/github.svg)](https://agentmods.dev/skills/scott-fryxell/brayness/nvim-buffers)
Your own site
<a href="https://agentmods.dev/skills/scott-fryxell/brayness/nvim-buffers"><img src="https://agentmods.dev/badge/skills/scott-fryxell/brayness/nvim-buffers/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for nvim-buffers

Your own site · 80×15
<a href="https://agentmods.dev/skills/scott-fryxell/brayness/nvim-buffers"><img src="https://agentmods.dev/badge/skills/scott-fryxell/brayness/nvim-buffers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 962 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.00962
Opus 5 $0.00047 $0.00481
Sonnet 5 $0.00019 $0.00192
Haiku 4.5 $0.00009 $0.00096

Measured 10d ago against content hash 2c8136476cc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

nvim-buffers 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 10d ago.

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.

skills/nvim-buffers/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nvim Buffers

The user runs LazyVim (~/.config/nvim, config in work/nvim). An autocmd in lua/config/autocmds.lua writes the open real-file buffers to a state file on every buffer change. Read that file with the read tool (or cat) to see what they're working on.

Path

~/.local/state/nvim/open-buffers.json (vim.fn.stdpath("state") on macOS)

Shape

{
  "current": "/abs/path/to/current/buffer",
  "buffers": ["/abs/path/a", "/abs/path/b"],
  "oil": [{ "dir": "/browsed/dir", "highlighted": "file.lua" }],
  "view": {
    "file": "/abs/path",
    "line": 42,
    "col": 3,
    "visible": { "from_top": 30, "to_bottom": 60 },
    "context": ["line 40", "line 41", "line 42"]
  },
  "updated": "2026-08-11T14:01:00"
}
  • current - the active buffer; null or an oil dir if the active buffer is a terminal/oil/unnamed buffer.
  • buffers - sorted list of all listed real-file buffers (term://, oil://, unnamed excluded).
  • oil - directories currently browsed in oil (strips the oil:// prefix), each with highlighted - the entry name under the cursor in that oil window, or null if the oil buffer isn't shown in a window right now.
  • view - the active window: file, cursor line/col, visible top/bottom lines, and a few lines of context around the cursor. Use this to answer "what's on my screen" / "what am I looking at" / "what should I press here".
  • updated - when nvim last wrote it. Check it's fresh before trusting it.

Freshness: refreshed on buffer events + FocusGained + a 5s timer; external file changes are reloaded (never clobbering unsaved edits).

Coaching role (training wheels)

The user is still learning vim and runs hardtime.nvim, which blocks/"yells" at inefficient keys. Be the patient counterpart:

  • When they ask how to do something, teach from THEIR config (work/nvim/, lua/config/keymaps.lua, lua/plugins/*.lua), never generic defaults.
  • One key at a time, tied to what their view shows.
  • Read the state file first and confirm what they're looking at before answering, so hints land on their real cursor position.
  • Their notable bindings: - = Oil parent dir, <leader>gg/<leader>gG = gitui, gr = LSP references, <leader>fb = buffers (Snacks), <leader>fg = grep, gd/gi = LSP definition/implementation, K = hover. Git + search are LazyVim defaults (<leader>g..., <leader>f...).

Read the full file on GitHub · 75 lines

Changes

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.

  1. 10d ago First seen · 75 lines · 94 tokens per session scan A 2c8136476cc3

Subscribe to this mod's changes

nvim-buffers is a skill published in the GitHub repository scott-fryxell/brayness (120 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 962 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens