og-cli: Skill for Claude Code

.claude/skills/og-workspaces/SKILL.md

og-workspaces is a skill for Claude Code from carlosprados/og-cli. It costs 80 tokens per session (4,318 once invoked), scanned A, original, Apache-2.0.

A workflow for editing and deploying OpenGate workspaces, dashboards, and widgets through the `og` command-line tool. OpenGate is a service where workspaces contain dashboards made of grid-based widgets.

In plain words
What is it for?
It is for pulling, modifying, wrapping, and deploying OpenGate workspaces, dashboards, and widgets while preserving their order and layout.
Why use it?
It turns remote dashboard structures into editable local files and back again, including embedded JavaScript and cross-tenant migration steps.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is carlosprados/og-cli's own configuration. It tells Claude Code how to work on og-cli itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything og-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to carlosprados/og-cli. 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/carlosprados/og-cli/main/.claude/skills/og-workspaces/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/carlosprados/og-cli

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.

agentmods badge for og-workspaces

README.md
[![agentmods](https://agentmods.dev/badge/skills/carlosprados/og-cli/og-workspaces/github.svg)](https://agentmods.dev/skills/carlosprados/og-cli/og-workspaces)
Your own site
<a href="https://agentmods.dev/skills/carlosprados/og-cli/og-workspaces"><img src="https://agentmods.dev/badge/skills/carlosprados/og-cli/og-workspaces/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 og-workspaces

Your own site · 80×15
<a href="https://agentmods.dev/skills/carlosprados/og-cli/og-workspaces"><img src="https://agentmods.dev/badge/skills/carlosprados/og-cli/og-workspaces.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,318 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 $0.00080 $0.04318
Opus 5.5 $0.00032 $0.01727
Sonnet 5.5 $0.00016 $0.00864
Haiku 4.5 $0.00008 $0.00432

Measured 1mo ago against content hash 1ee5b604d0f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

og-workspaces 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 1mo 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/og-workspaces/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenGate Workspaces skill

Workspaces are the OpenGate UI top-level containers (Web API /api/v1); each workspace owns N dashboards; each dashboard is a grid of widgets. The og CLI turns them into an editable local directory tree (pull) and back (wrap/deploy), extracting embedded JavaScript into real .js files.

Prerequisite: og login WITHOUT --no-web (workspace/dashboard commands use the Web API token). Quirk: OpenGate allows one active web session per user — a browser login steals the CLI session; og re-signs-in automatically on 401.

Local directory structure (what pull produces / wrap expects)

wsroot/
└── <workspace-slug>/                          # e.g. dashboards-adif
    ├── workspace.json                         # metadata only — dashboards array is STRIPPED
    └── NN__<dashboard-slug>/                  # NN__ prefix preserves array order, e.g. 00__visualizaci-n-pbi
        ├── dashboard.json                     # dashboard metadata + _workspaceLayout block
        └── NN__<widget-type>__<wid>/          # e.g. 00__customchart__1727269767709-0
            ├── widget.json                    # GridItem: layout (x,y,w,h,i) + definition
            └── _widgetConfigCode.js           # extracted JS (when present)

Rules:

  • workspace.json MUST NOT embed the dashboards array — the CLI derives it from subdirectories.
  • dashboard.json MUST include _workspaceLayout (x,y,w,h,id) linking it to the workspace grid.
  • widget.json MUST be a full GridItem (layout coords AND definition), not a bare widget config.
  • JS extraction is DECLARED, not guessed. Widget code fields, matched at any depth: _widgetConfigCode, _formatterCode, formatter, script, code, fn, expression. A declared field becomes a sibling .js file whenever present — even when empty — so its filename never moves because you edited the code. Nested fields keep their keypath in the filename (columns__0__formatter.js, columns__2___formatterCode.js). Edit the .js files, NOT the JSON copies.
  • operation is NOT a code field: it carries an operation name (REFRESH_INFO).
  • Transitional fallback (widgets only): an UNDECLARED field whose content looks like JavaScript (long, with function/return/=>/const/let/var) is still extracted, but pull prints a hint: on stderr naming it. Report those so the field gets declared — the heuristic misses code written as a bare assignment, and fires on prose.
  • A .js file the family does not declare (your own helper.js, generated typings) is IGNORED by wrap — reported with a hint:, never uploaded as a payload field.
  • The cycle is content-lossless in the sense that wrap reproduces an equivalent widget config: the decoded JSON trees compare equal. It is NOT a byte-for-byte or SHA256 match — key order and null/default serialisation differ. Two real round-trip defects (an object keyed by number turning into an array; a key containing __ colliding with the separator) were fixed in v2.1.0.

Read the full file on GitHub · 302 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. 1mo ago Changed · +15 lines 1ee5b604d0f2
  2. 2mo ago Changed · +7 lines a2edc878c7a0
  3. 2mo ago First seen · 280 lines · 80 tokens per session scan A 388a078e8517

Subscribe to this mod's changes

og-workspaces is a skill published in the GitHub repository carlosprados/og-cli (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 4,318 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 2026-08-31.

Related

og-workspaces compared with skills from other repositories

og-workspaces next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
og-workspacescarlosprados/og-cliSkill21mo agoApache-2.0A80Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code