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 skills add Schimmilab/ipsymcon-mcp-server --skill ips-automationgit clone --depth 1 https://github.com/Schimmilab/ipsymcon-mcp-serverWrote 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/schimmilab/ipsymcon-mcp-server/ips-automation)<a href="https://agentmods.dev/skills/schimmilab/ipsymcon-mcp-server/ips-automation"><img src="https://agentmods.dev/badge/skills/schimmilab/ipsymcon-mcp-server/ips-automation.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 | $0.00048 | $0.00606 |
| Opus 5 | $0.00024 | $0.00303 |
| Sonnet 5 | $0.00010 | $0.00121 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
ips-automation 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 7d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IP-Symcon — designing an automation
Build an automation that still works in six months and whose state you can see and
prove. The ipsymcon skill covers how to call things safely; this one covers what to
build — the design decisions where automations silently fail.
REQUIRED BACKGROUND: the ipsymcon skill — same MCP, same plan-before-you-touch rule,
same ID resolution. This is design guidance on top, not a replacement.
Full procedure, patterns and the failure catalogue: references/workflow.md.
The five rules that prevent silent failure
-
Every tunable is a variable, never a literal. Times, thresholds, delays, windows — each gets its own variable with a profile (range + unit) and an action script, so it is adjustable from the visualisation. A threshold hardcoded in a script is a threshold nobody will ever tune.
-
Pick thresholds from the spread, not from the means. Look at min/max of both states before choosing. Two averages 20 apart can still overlap at the edges; the automation then flaps. Decide on the gap between the ranges.
-
A sliding window is blind at every state change. Any "max/avg over the last N minutes" still describes the old state right after a switch. Handle transitions explicitly — a grace period after switching on, and an authoritative signal (the switch command itself) rather than the look-back for "is it on?".
-
Mirror a working example; never trust the API doc alone. Before configuring an event, read the config of an event that demonstrably runs in this system and copy its field combination. Then verify with
NextRun— active is not scheduled. -
Prove it at the Ist, end to end. Trigger the real path and read the real result. A config that looks right is not evidence. And announce live switching whenever the device might be in use.
Never
- Never leave scripts, action helpers and timestamps visible in the visualisation — hide the machinery, show only what is operated or read.
- Never build a condition on a variable without checking
VariableUpdatedfirst: IPS carries the last value forward forever, so a dead source looks like a stable reading. - Never poll a device with an exclusive connection while separately probing it — your own diagnostics become the fault you then explain.
What ships with it
1 file 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.
- 7d ago First seen · 50 lines · 48 tokens per session scan A fdd8f37ccee0
ips-automation is a skill published in the GitHub repository Schimmilab/ipsymcon-mcp-server (0 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 606 once invoked, about $0.0002 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
home-assistant-rest
Control and query Home Assistant through the connector's callservice tool — REST API patterns, common domains, how to find entities before acting.
devices-mcp-home
Live inventory of the user's smart home on this devices-mcp installation — cameras, Hue lights, Tapo P115 plugs, Netatmo weather, Ring, Nest Protect, Shelly sensors, and robots. Use when the user asks what devices they have, what's online, or wants a status summary before controlling hardware.
unifi-network
How to manage UniFi network infrastructure — devices, clients, firewall, VPN, routing, WLANs, Traffic Flows, and statistics. Use this skill when the user mentions UniFi, Ubiquiti, network management, WiFi configuration, firewall rules, port forwarding, VPN, QoS, bandwidth, traffic flows, connected clients, network…
unifi-protect
How to manage UniFi Protect cameras and NVR — view cameras, smart detections, Find Anything detection search, recordings, snapshots, lights, sensors, Known Faces, license plates, and the Alarm Manager. Use this skill when the user mentions UniFi cameras, security cameras, NVR, recordings, motion detection, person…
unifi-access
How to manage UniFi Access door control — locks, credentials, visitors, access policies, and events. Use this skill when the user mentions UniFi Access, door locks, door access, building access, NFC cards, PIN codes, visitor passes, access policies, access schedules, door readers, or any UniFi Access task.
network-health-check
Run a UniFi network health check — diagnose device status, connectivity issues, firmware updates, and system health. Use when asked to check network health, find what's down, diagnose connectivity issues, or get a network status summary.