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 tikoci/routeros-skills --skill routeros-cmrgit clone --depth 1 https://github.com/tikoci/routeros-skillsWrote 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/tikoci/routeros-skills/routeros-cmr)<a href="https://agentmods.dev/skills/tikoci/routeros-skills/routeros-cmr"><img src="https://agentmods.dev/badge/skills/tikoci/routeros-skills/routeros-cmr/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.
<a href="https://agentmods.dev/skills/tikoci/routeros-skills/routeros-cmr"><img src="https://agentmods.dev/badge/skills/tikoci/routeros-skills/routeros-cmr.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00152 | $0.03045 |
| Opus 5.5 | $0.00061 | $0.01218 |
| Sonnet 5.5 | $0.00030 | $0.00609 |
| Haiku 4.5 | $0.00015 | $0.00304 |
Grade A, and why
routeros-cmr 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 9d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RouterOS CMR
Grounded on RouterOS 7.26beta1, x86 CHR, with four disposable routers and three quickchr socket links. The controller, a transit client, a remote client reachable through OSPF, and a direct discovery client exercise different paths. The [runnable example][example] and [evidence report][report] are the reproduction surface. No later beta, arm64 CHR or WiFi radio was verified by this lab.[^lab]
CMR manages RouterOS devices: inventory, resource/availability/log alerts, fleet scripts and upgrades, topology, and WiFi/VLAN provisioning. It does not provide general ping/SNMP/HTTP monitoring of non-RouterOS equipment.[^docs]
Versions and packages
CMR first appeared in 7.26beta1. Pin that version for reproductions and record
both the controller and client versions. The lab installed the optional cmr
package only on the controller; clients used the built-in /cmr/client.[^lab]
The manual lists arm, arm64 and x86 for the server package. Clients exclude smips and powerpc. A mipsbe client was observed in the earlier hardware session; that architecture was not re-tested in the CHR lab.[^docs][^prior]
Server, service and client discovery
/cmr set enabled=yes track-topology=yes fetch-comments=yes auto-labels=all
The controller lists its own built-in client in /cmr/device. A dynamic service
named cmr listens on TCP/54321. Scope this service with the input firewall.
In the lab, CMR was blocked on each host-management NIC so pairing used only the
socket topology.[^lab]
/cmr/client set enabled=yes controller-addresses=10.255.0.1
The remote client reached that controller loopback through a transit router,
with an asserted active OSPF route. A direct client with no
controller-addresses discovered the controller on its socket link. DHCP-based
discovery and application traffic collection remain manual-only claims.[^lab][^docs]
Read /cmr/client for status, pairing-status, controller-address and
controller-identity. The lab observed waiting-for-pairing,connected becoming
paired,connected. Paired clients reconnected with pairing intact after a clean
/system/reboot, a hard power-off and a controller reboot.[^lab]
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.
- 9d ago First seen · 247 lines · 152 tokens per session scan A 0534190e869a
routeros-cmr is a skill published in the GitHub repository tikoci/routeros-skills (74 stars, last pushed yesterday), licensed MIT. It adds 152 tokens to every session and 3,045 once invoked, about $0.0006 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 2026-10-07.
Other skills, from other repositories
lab-hardware-cad
Designs custom laboratory hardware as parametric build123d models and exports fabrication artifacts as STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a…
pylabrobot
Develops and reviews PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Supports PyLabRobot protocols and API questions; keep physical execution behind an explicit operator safety gate.
pybamm
Simulates lithium-ion battery charge, discharge and rest experiments with PyBaMM, records parameter-set provenance, checks mesh and solver sensitivity, and compares predicted voltage curves with measured cycling data. Use for SPM or DFN electrochemical battery modeling, C-rate protocols, voltage cutoffs, parameter…
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…
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…
offensive-iot
IoT and embedded device security testing methodology. Covers hardware reconnaissance (UART, JTAG, SWD, SPI flash, I2C EEPROM, eMMC chip-off), firmware acquisition (vendor portals, OTA capture, flash dump, binwalk extraction), firmware analysis (filesystem mounting, binary triage, hardcoded secrets, default credential…