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/carlosprados/og-cli/og-workspacesnpx skills add carlosprados/og-cli --skill og-workspacesgit clone --depth 1 https://github.com/carlosprados/og-cliWrote 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/carlosprados/og-cli/og-workspaces)<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="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 | $0.03948 |
| Opus 5 | $0.00040 | $0.01974 |
| Sonnet 5 | $0.00016 | $0.00790 |
| Haiku 4.5 | $0.00008 | $0.00395 |
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 3d 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 — 280 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.jsonMUST NOT embed thedashboardsarray — the CLI derives it from subdirectories.dashboard.jsonMUST include_workspaceLayout(x,y,w,h,id) linking it to the workspace grid.widget.jsonMUST be a full GridItem (layout coords ANDdefinition), 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.jsfile 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.jsfiles, NOT the JSON copies. operationis 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, butpullprints ahint: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
.jsfile the family does not declare (your ownhelper.js, generated typings) is IGNORED by wrap — reported with ahint:, never uploaded as a payload field. - The cycle is content-lossless in the sense that
wrapreproduces 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.
What ships with it
24 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.
- reference/AreasList.md 1.3 KB
- reference/browsers.md 4.7 KB
- reference/clock.md 663 B
- reference/commonFields.md 7.4 KB
- reference/customChart.md 5.3 KB
- reference/customTable.md 7.2 KB
- reference/dashboards.md 3.9 KB
- reference/datamodel.md 10 KB
- reference/DatapointsList.md 2.5 KB
- reference/DeviceAlarmsList.md 2.2 KB
- reference/ExecutionsList.md 8.3 KB
- reference/FullDevicesList.md 946 B
- reference/iframeWidget.md 2.1 KB
- reference/ListsCommons.md 11 KB
- reference/markdown.md 2.2 KB
- reference/OperationsList.md 4.8 KB
- reference/rulesBrowser.md 1.5 KB
- reference/TableDataset.md 2.2 KB
- reference/TimeseriesList.md 2.7 KB
- reference/UsersList.md 1.7 KB
- reference/utils.md 3.8 KB
- reference/widget-js-api.md 10 KB
- reference/windowFilterVariants.md 2.6 KB
- reference/workspaces.md 9.2 KB
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.
- 3d ago First seen · 280 lines · 80 tokens per session scan A 388a078e8517
og-workspaces is a skill published in the GitHub repository carlosprados/og-cli (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 80 tokens to every session and 3,948 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…