agentmods.dev

openshell-dashboard CLAUDE.md

openshell-dashboard CLAUDE.md is an instructions file for coding agents from Gkrumbach07/openshell-dashboard. It costs 1,005 tokens per session, scanned A, original, Apache-2.0.

Project instructions for OpenShell Dashboard, a web administration interface with a React frontend and a Go backend that communicates with OpenShell through gRPC, a service-to-service communication system.

In plain words
What is it for?
Use it when working on dashboard pages, shared components, REST handlers, backend gateway code, or generated protocol code.
Why use it?
It explains the repository layout, architecture, build process, and API boundaries so changes are made in the expected parts of the project.

Instructions file

not rated 2 changed yesterday A scan 1,005 tokens original Apache-2.0
View the source file Gkrumbach07/openshell-dashboard
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.

agentmods
npx agentmods add instructions/gkrumbach07/openshell-dashboard/claude-md
Clone the repo
git clone --depth 1 https://github.com/Gkrumbach07/openshell-dashboard

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 openshell-dashboard CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gkrumbach07/openshell-dashboard/claude-md.svg)](https://agentmods.dev/instructions/gkrumbach07/openshell-dashboard/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/gkrumbach07/openshell-dashboard/claude-md"><img src="https://agentmods.dev/badge/instructions/gkrumbach07/openshell-dashboard/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,005 This file is loaded in full into every session.
When invoked 1,005 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01005 $0.01005
Opus 5 $0.00502 $0.00502
Sonnet 5 $0.00201 $0.00201
Haiku 4.5 $0.00101 $0.00101

Measured yesterday against content hash f0172e4051ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openshell-dashboard 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 yesterday.

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.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.

OpenShell Dashboard

Standalone web admin UI for OpenShell. Go BFF + React frontend. Talks to the OpenShell gateway through the vendored Go SDK.

Project structure

frontend/           React + TypeScript + PatternFly 6
  src/app/          App shell, routing (App.tsx), layout, theme
  src/pages/        Page components — flat files, exported for downstream
  src/components/   Shared components
  src/api/          REST client (client.ts), hooks, queryKeys.ts
  src/hooks/        Custom hooks (useBulkDelete, useListPage, useTableSelection)
  src/slots/        SlotProvider context for downstream UI injection
  src/types/        TypeScript interfaces
  src/utils/        Formatters and helpers
backend/            Go BFF
  cmd/              Entry point
  internal/api/     REST handlers (respond.go helpers, *_handler.go)
  internal/auth/    Proxy-delegated token extraction (proxy.go)
  internal/sdkclient/ SDK auth helper + raw exec escape hatch for binary-safe uploads
  internal/models/  Response DTOs (From*() converters) and request builders
scripts/            Dev environment (dev-env.sh — Keycloak + gateway setup)
docs/adrs/          Architecture Decision Records

Build and run

make setup          # install frontend + go deps
make dev            # start frontend dev server + BFF with hot reload
make dev-full       # start Keycloak + gateway + dashboard (full OIDC stack)
make build          # produce container image
make test           # frontend unit tests + go tests
make lint           # eslint + golangci-lint
make typecheck      # tsc --noEmit

Requires a running OpenShell gateway: openshell gateway start (Podman) or point OPENSHELL_GATEWAY_URL at an existing one.

Architecture rules

Each rule has a corresponding Architecture Decision Record in docs/adrs/. Read those for full context, alternatives considered, and consequences.

  • Downstream consumption (ADR 0001). Consumers install the npm package and get five base mechanisms: barrels, slots, self-contained pages with navigation callbacks, feature flags, runtime config (setApiBasePath). i18n is a sixth mechanism per ADR 0004 (./i18n barrel). Minimal co-located CSS (layout rules only, all values via PF tokens). Zero imports from any downstream platform.
  • Relay-only auth (ADR 0002). The BFF never terminates authentication — a fronting proxy (oauth2-proxy standalone, the host platform's proxy when embedded) owns login/sessions/refresh/CSRF and injects x-forwarded-access-token. Bearer chain: proxy header → Authorization: Bearer → 401. The BFF never validates tokens and never authorizes. The only auth switch is AUTH_DISABLED (dev).
  • Surface the API as-is. The upstream OpenShell API defines what exists — never invent RPCs, fields, lifecycle states, or abstractions (no Agent object; Sandbox is fundamental, labels categorize). See .claude/rules/openshell-api.md for the hard rules.
  • PatternFly 6 only. No MUI, no custom design system, no inline styles with hardcoded values.
  • Use the vendored Go SDK directly. Prefer github.com/NVIDIA/OpenShell/sdk/go over local wrappers or copied protos. The one intentional exception is internal/sdkclient/rawexec.go for binary-safe uploads because the public SDK still does not expose non-TTY exec with stdin.

Read the full file on GitHub · 64 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. yesterday Changed · -3 lines · +39 tokens per session f0172e4051ea
  2. 5d ago First seen · 67 lines · 966 tokens per session scan A 5697b45d0fb9

Subscribe to this mod's changes

openshell-dashboard CLAUDE.md is an instructions file published in the GitHub repository Gkrumbach07/openshell-dashboard (2 stars, last pushed today), licensed Apache-2.0. It adds 1,005 tokens to every session, about $0.0050 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens