A procedure for updating protocol definition files from NVIDIA’s OpenShell project and regenerating the Go code that represents them. Protocol files describe how software services communicate.

Use it when OpenShell’s protocol definitions change, then rebuild the Go backend and check whether new service operations need dashboard support.

It keeps the dashboard’s generated Go code aligned with upstream API changes and reveals breaking changes during the build.

How Gkrumbach07/openshell-dashboard configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Gkrumbach07/openshell-dashboard. 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/Gkrumbach07/openshell-dashboard/main/.claude/skills/proto-sync/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Gkrumbach07/openshell-dashboard

Made for: Claude Code.

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/gkrumbach07/openshell-dashboard/proto-sync/github.svg)](https://agentmods.dev/skills/gkrumbach07/openshell-dashboard/proto-sync)

Your own site

<a href="https://agentmods.dev/skills/gkrumbach07/openshell-dashboard/proto-sync"><img src="https://agentmods.dev/badge/skills/gkrumbach07/openshell-dashboard/proto-sync/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/gkrumbach07/openshell-dashboard/proto-sync"><img src="https://agentmods.dev/badge/skills/gkrumbach07/openshell-dashboard/proto-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,228 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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.01228
Opus 5.5	$0.00020	$0.00491
Sonnet 5.5	$0.00010	$0.00246
Haiku 4.5	$0.00005	$0.00123

Measured 24d ago against content hash b9cdee102012, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

proto-sync 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 24d 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.

.claude/skills/proto-sync/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDK Sync

The BFF reaches the gateway through the OpenShell Go SDK, and this repository holds no copy of the gateway's proto files and no generated stubs (ADR 0003). So there is nothing to regenerate: when OpenShell changes, the pinned SDK moves to the new release, and the handlers and models it affects are audited.

Before you start

You do not move the SDK. It moves together with the gateway the branch pins, to the commit of an upstream release tag, and a workflow makes that move (ADR 0005, decision 7; hard facts 17 and 20 in .claude/rules/openshell-api.md):

.github/workflows/follow-upstream.yml reads upstream's tags every hour. It keeps the next branch one commit ahead of main: the pins file, go.mod, go.sum, the built-in release line when the minor changes, and the README's generated block, all moved to the upcoming release. next pins the newest pre-release until upstream cuts the stable release, then that.
Never go get ...@latest or a branch. Never move the pins in a pull request of your own, never push to next, and never open its pull request.
If no next exists, upstream has nothing ahead of main (python3 deploy/ci/upstream/follow.py plan --out /tmp/plan.json says what it sees). If one should exist and does not, stop and say so.

What this skill is for is the work a move leaves: the BFF does not build against the new SDK, the compat suite fails on next, or a new capability is worth exposing. All of it is done on next: branch from it, and open the pull request into it. It cannot land on main, where the SDK is still the old one.

Steps

1. See what moved

git fetch origin
git log --oneline --reverse origin/main..origin/next   # the first line is the pin move
git diff origin/main origin/next -- deploy/ci/gateway-pins.json backend/go.mod

Then compare the two SDK versions:

sdk/go/openshell/v1/ for public client methods and resource shapes
sdk/go/openshell/v1/types/ for request/response field details
sdk/go/proto/sandboxv1/ only when the frontend policy protojson contract is involved

Read the full file on GitHub · 106 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.

24d ago Changed · +10 tokens per session b9cdee102012
27d ago Changed · -9 lines · +5 tokens per session efb43d73b9f0
1mo ago Changed · +1 lines b283799fdf37
1mo ago Changed · +59 lines 4f6b31070519
1mo ago Changed 610ec2d7f78b
2mo ago Changed · +5 lines · +1 tokens per session 535c391db2b2
2mo ago First seen · 50 lines · 33 tokens per session scan A 0f09d4ecb048

Subscribe to this mod's changes

proto-sync is a skill published in the GitHub repository Gkrumbach07/openshell-dashboard (5 stars, last pushed 10d ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,228 once invoked, about $0.0002 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 2026-08-31.

proto-sync next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
proto-syncGkrumbach07/openshell-dashboard	Skill	5	10d ago	Apache-2.0	A	49	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

openshell-dashboard: Skill for Claude Code