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-device-opsnpx skills add carlosprados/og-cli --skill og-device-opsgit 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-device-ops)<a href="https://agentmods.dev/skills/carlosprados/og-cli/og-device-ops"><img src="https://agentmods.dev/badge/skills/carlosprados/og-cli/og-device-ops.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 5.1 | $0.00164 | $0.06203 |
| Opus 5 | $0.00082 | $0.03102 |
| Sonnet 5 | $0.00033 | $0.01241 |
| Haiku 4.5 | $0.00016 | $0.00620 |
Grade A, and why
og-device-ops 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 — 446 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenGate device operations skill
Acting ON devices (vs querying them — that's the og-cli skill): operations,
alarms, and data injection. All commands need a logged-in profile (og login).
Destructive operations — confirm BEFORE running (HITL)
delete and cancel verbs are irreversible. og guards them: on an interactive
terminal it prompts [y/N]; non-interactively it REFUSES unless --yes is
passed (Error: refusing to delete ... re-run with --yes (no interactive terminal)). You drive og non-interactively, so that terminal prompt never reaches
the user — the safeguard is YOURS to honor:
- STOP before any destructive command. State exactly what it affects — verb, id,
org/channel, and what is lost (e.g. "delete device
sense-001in orgacme— removes the entity and its collected data"). - Ask the user and wait for an explicit yes.
- Only then run it with
--yes(required non-interactively).
Never add --yes reflexively to silence the "refusing…" error — that error means
ask the user first, not append a flag.
Destructive verbs: dev delete, jobs cancel, tasks cancel, dm delete,
connectors delete, rules delete, optypes delete, provision delete,
timeseries delete, datasets delete, workspace delete, dashboard delete.
Treat deploy --update (overwrites) and bulk provision runs as high-impact too —
confirm scope first.
Jobs — one-shot operations on devices
A job = an operation (REBOOT_EQUIPMENT, EQUIPMENT_DIAGNOSTIC, ...) targeted at N devices, with schedule/timeout/retry semantics. Lifecycle:
og jobs create -f job.json # launch, ONE batch (max 100 entities)
og jobs launch -f job.json --entities-file ids.txt # any fleet size, batched
og jobs get <job-id> # report: report.summary.status
og jobs operations <job-id> --all # per-device results — check THIS for partial failures
og jobs history --job <job-id> --all # same results, filterable, across jobs
og jobs cancel <job-id> # stop a running job
og jobs search -w "jobStatus eq IN_PROGRESS"
og jobs search -w "operationName eq REBOOT_EQUIPMENT"
What ships with it
4 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 · 446 lines · 164 tokens per session scan A 700ae4dea3c6
og-device-ops is a skill published in the GitHub repository carlosprados/og-cli (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 164 tokens to every session and 6,203 once invoked, about $0.0008 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
integrated-browser
Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…