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 Knuckles-Team/systems-manager --skill ipmi-bmc-managergit clone --depth 1 https://github.com/Knuckles-Team/systems-managerWrote 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/knuckles-team/systems-manager/ipmi-bmc-manager)<a href="https://agentmods.dev/skills/knuckles-team/systems-manager/ipmi-bmc-manager"><img src="https://agentmods.dev/badge/skills/knuckles-team/systems-manager/ipmi-bmc-manager.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 | $0.00093 | $0.01594 |
| Opus 5 | $0.00046 | $0.00797 |
| Sonnet 5 | $0.00019 | $0.00319 |
| Haiku 4.5 | $0.00009 | $0.00159 |
Grade B, and why
ipmi-bmc-manager scanned grade B with 1 finding 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 6d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **In-band** — running on the target's own OS: `sudo ipmitool <cmd>` (no IP/creds; talks to How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IPMI / BMC Manager Skill
Stateless atomic operations against a server's baseboard management controller (BMC) — the always-on management processor (Dell iDRAC, HPE iLO, Supermicro, or generic IPMI 2.0). The BMC is independent of the host OS: it answers even when the OS is down or the machine is powered off (as long as it has standby power). This makes it the reliable path for remote power control and out-of-band recovery after a change locks you out of SSH (bad netplan, firewall, kernel panic).
Prerequisites
ipmitoolon the controlling host (apt-get install -y ipmitool). It loadsipmi_si+ipmi_devintfand creates/dev/ipmi0for in-band access.- Access path (one of):
- In-band — running on the target's own OS:
sudo ipmitool <cmd>(no IP/creds; talks to the local BMC over the KCS interface at/dev/ipmi0). - Out-of-band — over the network to the BMC's IP:
ipmitool -I lanplus -H <BMC_IP> -U <user> -P <pw> <cmd>.
- In-band — running on the target's own OS:
systems-manager-mcp(optional) to executeipmitoolon remote hosts over SSH when you don't have a session on the target.
Never hardcode BMC passwords in scripts/commits. Read from an env/secret. Default Dell iDRAC creds are
root/calvin— assume they should be rotated.
Operations
1. Discover / verify the BMC
sudo ipmitool mc info # vendor, firmware, IPMI version
sudo ipmitool lan print 1 # BMC network config on channel 1 (often 1; iLO may use 2)
ls /dev/ipmi* # in-band device present?
Capture: manufacturer (Dell/HPE/Supermicro), firmware, BMC IP, IP source (static/dhcp), channel.
2. Power & chassis control
ipmitool ... chassis status # current power state
ipmitool ... power status
ipmitool ... power on | off | cycle | reset | soft
ipmitool ... chassis identify 30 # blink the locator LED 30s
ipmitool ... chassis bootdev pxe|disk|bios # one-time next-boot device
Prefer power cycle/reset over off for recovery (avoids leaving a node down).
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.
- 6d ago First seen · 129 lines · 93 tokens per session scan B 76e0159102c8
ipmi-bmc-manager is a skill published in the GitHub repository Knuckles-Team/systems-manager (3 stars, last pushed 9d ago), licensed MIT. It adds 93 tokens to every session and 1,594 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hardware-health-check
Out-of-band hardware health via Redfish BMC (read-only) — power state, component health, thermal and power readings, firmware inventory, SEL log triage. Use when determining whether a host is powered off versus unreachable, checking hardware faults, reviewing thermal or PSU state, or triaging BMC event logs.
percepxion-oob
Manage Lantronix out-of-band (OOB) infrastructure via Percepxion central management platform: device inventory, serial port inspection via SLC CLI, firmware compliance, config management, security auditing, and closed-loop incident remediation. Use during outages, maintenance windows, compliance cycles, and…
kvm-pilot
AI-driven bare-metal control of headless machines through IP-KVMs (PiKVM, GL.iNet GLKVM GL-RM1/RM1PE, BliKVM), server BMCs (Redfish iDRAC/iLO/XCC, IPMI), and Intel AMT/vPro. Use whenever the user wants to remotely operate, install, or recover a physical machine: power on/off/cycle, mount an install ISO, set the next…
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…
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.