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 skills/moeru-ai/auv/use-buf-pluginsnpx skills add moeru-ai/auv --skill use-buf-pluginsgit clone --depth 1 https://github.com/moeru-ai/auvWrote 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/skills/moeru-ai/auv/use-buf-plugins)<a href="https://agentmods.dev/skills/moeru-ai/auv/use-buf-plugins"><img src="https://agentmods.dev/badge/skills/moeru-ai/auv/use-buf-plugins.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 | $0.00080 | $0.01043 |
| Opus 5 | $0.00040 | $0.00522 |
| Sonnet 5 | $0.00016 | $0.00209 |
| Haiku 4.5 | $0.00008 | $0.00104 |
Grade A, and why
use-buf-plugins 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use Buf Plugins
Make code generation reproducible across languages and environments. Prefer an established generator, pin its version, preserve source-relative package structure, and verify generated output.
Inspect the Existing Generation Contract
- Read repository instructions, every applicable
buf.gen*.yaml, generation script, CI workflow, package manifest, and generated directory convention. - Identify each required artifact: message runtime, gRPC client/server, gateway, OpenAPI, language typing, or framework bindings.
- Record plugin source, version/revision, options, invocation strategy, input scope, output path, and runtime requirements.
- Do not replace a working generator or rearrange generated paths without an explicit requirement.
Choose Remote or Local Deliberately
Use a BSR remote plugin when network access is reliable and centralized execution is acceptable. Pin the upstream plugin version and revision when available; do not rely on latest for reproducible generation.
Use a local plugin when:
- generation must work offline or in an isolated network;
- the BSR is unavailable;
- authentication or codegen rate limits make remote generation unreliable;
- a private/custom plugin cannot run remotely;
- CI requires locally controlled binaries or images.
Remote generation sends the Protobuf input to the configured BSR executor. Confirm that this is acceptable for private schemas. Authenticate with the repository's approved mechanism when increased BSR limits are needed; never embed tokens in config.
Read references/remote-and-local.md before changing plugin execution mode.
Source and Package Local Plugins Reproducibly
- Prefer the plugin author's official binary/package or the upstream definitions in
bufbuild/plugins. - Treat each upstream plugin Dockerfile, version, and revision as immutable build input.
- A maintained mirror may build selected upstream
bufbuild/pluginsDockerfiles into OCI images. Verify its source mapping, image entrypoint, version tag, platforms, provenance, and update cadence before depending on it. - If using a maintained
buf-buildmirror, understand the convention: an upstream path likeplugins/<family>/<plugin>/<version>/Dockerfileis published as an image whose repository identifies<family>-<plugin>and whose tag identifies<version>. Reinspect the mirror documentation instead of hardcoding one publisher, version, or registry. - If the maintained image is acceptable, consume a pinned digest or immutable version. Otherwise build the upstream definition locally.
- Invoke
$use-docker-buildx-for-buildingbefore building or smoke-testing any plugin OCI image. Follow its platform,--load, naming, secret, runtime, and cleanup requirements.
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.
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.
- 5d ago First seen · 68 lines · 80 tokens per session scan A 106a4a7f32b7
use-buf-plugins is a skill published in the GitHub repository moeru-ai/auv (25 stars, last pushed 5d ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,043 once invoked, about $0.0004 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 skills, from other repositories
axstream
Fast deterministic macOS UI automation via replayable macros. Use BEFORE driving any macOS app's UI by hand (clicking/typing via computer-use or screenshots) — if a macro exists, replay finishes the task in seconds with no per-step reasoning; after doing a UI task manually, save it as a macro so the next run is fast.…
open-compute-bridge
Bindet das model-agnostische Computer-Use-Modul open-compute (Screenshot-Wahrnehmung, Windows-UIA-Elementklicks, sicherheitsgegatete Aktionen) fuer ALLE Agenten des Systems ein -- Claude Code, Codex und agy/Antigravity. Nutzen, wenn ein Dienst eine interaktive GUI- oder Browser-Aktion braucht, die kein reiner…
computer-use
Drive macOS apps in the background using the background-computer-use MCP tools. Use when the user asks you to click inside another app, automate a GUI, type into a specific app, read an app's UI, or "use my Mac" without moving the cursor or focusing the app. Also use when the user mentions apps by name (Safari…
chrome
Google Chrome heuristics for background-computer-use. Use when the user asks you to navigate, scroll, click links, fill forms, or otherwise drive Chrome without stealing focus. Also applies to Chromium-family browsers (Brave, Edge, Arc) that share the same AppleScript JavaScript execution primitive.
apple-music
Apple Music (Music.app) playback and search heuristics for background-computer-use. Use when the user asks you to play a song, add to the queue, adjust volume, or search the library via Apple Music.
notion
Notion-specific heuristics for driving the Notion desktop app via background-computer-use. Use when the user asks you to edit a Notion page, add a block, create a database row, or otherwise interact with Notion's UI.