Guidance for using the Buf command-line tool with Protobuf workspaces and modules. It covers dependency management, formatting, linting, compatibility checks, and generating code from `.proto` files.

Use it when working with `buf.yaml`, `buf.lock`, `buf.gen.yaml`, Protobuf dependencies, lint rules, breaking-change checks, or code-generation commands.

It provides a consistent way to inspect and maintain Protobuf configuration before changing schemas. It also helps detect invalid dependencies, style problems, breaking API changes, and incorrect generated outputs.

How moeru-ai/auv configures Codex

Reuse

Borrowing it

Nothing to install: this file belongs to moeru-ai/auv. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/moeru-ai/auv/main/.agents/skills/use-buf/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/moeru-ai/auv

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/moeru-ai/auv/use-buf/github.svg)](https://agentmods.dev/skills/moeru-ai/auv/use-buf)

Your own site

<a href="https://agentmods.dev/skills/moeru-ai/auv/use-buf"><img src="https://agentmods.dev/badge/skills/moeru-ai/auv/use-buf/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/moeru-ai/auv/use-buf"><img src="https://agentmods.dev/badge/skills/moeru-ai/auv/use-buf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 845 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00070	$0.00845
Opus 5.5	$0.00028	$0.00338
Sonnet 5.5	$0.00014	$0.00169
Haiku 4.5	$0.00007	$0.00085

Measured 2mo ago against content hash b2a369e40295, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

use-buf 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 2mo 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.

.agents/skills/use-buf/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use Buf

Use the Buf CLI as the source of truth for Protobuf compilation, dependency resolution, linting, breaking-change detection, and code generation.

Inspect Before Changing

Read repository instructions.
Search the repository root and likely API directories for buf.yaml, buf.lock, buf.gen.yaml, and buf.gen.<domain>.yaml files.
Inspect the configuration version, module paths, dependency declarations, lint policy, breaking policy, inputs, plugin pins, output paths, and existing generation scripts.
Run buf --version and check repository/CI tool pins before using features from a newer configuration schema.
Diagnose configuration or dependency problems before changing .proto files to work around them.

Use one default buf.gen.yaml. Introduce buf.gen.<domain>.yaml only when generation products genuinely require isolated plugin sets, inputs, or outputs. Pass non-default templates explicitly with buf generate --template <file>.

Keep Configuration Responsibilities Clear

Use buf.yaml for workspaces/modules, BSR dependencies, lint rules, breaking rules, policies, and Buf check plugins.
Use buf.gen.yaml or buf.gen.<domain>.yaml for protoc-gen-* code-generation plugins, inputs, output directories, options, and managed mode.
Use buf.lock as generated dependency resolution state. Do not edit it manually.
Keep configuration in the repository root or the established API workspace directory unless repository structure requires otherwise.

Read references/configuration.md before adding modules, dependencies, check plugins, generation templates, or output paths.

Manage Dependencies Deliberately

Prefer BSR modules for maintained dependencies, including Google APIs, well-known types, Protovalidate, and grpc-gateway annotations.
Add or remove dependencies in buf.yaml, then run buf dep update and inspect the buf.lock diff.
Use buf dep graph --format json to identify the resolved dependency chain.
Use buf dep prune only after confirming an import is genuinely unused.
When a type appears missing, inspect configuration and the lockfile, run buf dep update, then run buf build or buf generate to obtain the compiler's concrete import/type error.
Never hardcode an operating system's Buf cache location. Export the pinned module with buf export when source inspection is required.

Read the full file on GitHub · 64 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 64 lines · 70 tokens per session scan A b2a369e40295

Subscribe to this mod's changes

use-buf is a skill published in the GitHub repository moeru-ai/auv (203 stars, last pushed 2d ago), licensed Apache-2.0. It adds 70 tokens to every session and 845 once invoked, about $0.0003 per session on Opus 5.5. 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.

Backend and APIs agent-desktop computer-use cua gui-automation os-automation phone-use

use-buf next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
use-bufmoeru-ai/auv	Skill	203	2d ago	Apache-2.0	A	70	Codex
telegramrazzant/ouroboros	Skill	1.6k	today	MIT	A	19	Claude Code
computer-use-safetyellmos-ai/skills	Skill	9	3d ago	MIT	A	186	Claude Code, Codex
open-compute-bridgeellmos-ai/skills	Skill	9	3d ago	MIT	B	149	Claude Code, Codex
oswrightAsk-812/oswright	Skill	4	21d ago	MIT	A	97	Claude Code, Codex
axstreammilind-soni/axstream	Skill	20	2mo ago	MIT	A	96	Claude Code
computer-useedosulai/silenthand-cua	Skill	0	2mo ago	MIT	A	37	Claude Code, Codex

auv: Skill for Codex