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/rhtevan/agentfs/crc-ctlnpx skills add rhtevan/agentfs --skill crc-ctlgit clone --depth 1 https://github.com/rhtevan/agentfsWrote 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/rhtevan/agentfs/crc-ctl)<a href="https://agentmods.dev/skills/rhtevan/agentfs/crc-ctl"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/crc-ctl.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 | $0.00026 | $0.02449 |
| Opus 5 | $0.00013 | $0.01224 |
| Sonnet 5 | $0.00005 | $0.00490 |
| Haiku 4.5 | $0.00003 | $0.00245 |
Grade A, and why
crc-ctl 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRC Cluster Control
Operational procedures for starting, stopping, and maintaining the
OpenShift Local (CRC) cluster. This skill defines the correct workflow
for using the custom crcstart and crcstop wrapper scripts, and
provides a disk cleanup procedure to reclaim space inside the CRC VM
when container image layers, journal logs, and completed pods
accumulate over time.
Important: Never use the built-in
crc startorcrc stopcommands directly. Always use thecrcstartandcrcstopwrapper scripts. See thecrc-cmdskill for installation details.
Harvested From
| Project | Source | Entry |
|---|---|---|
| ~/app/playground/goofing-around | default-agent/MEMORY | "Do NOT use crc start or crc stop — use crcstart and crcstop instead" |
| ~/app/playground/goofing-around | default-agent/MEMORY | "Before running crcstart, first run crc version and show the result" |
| ~/app/playground/goofing-around | default-agent/MEMORY | "After running crcstop, wait for exit, check for lingering CRC processes, clean up" |
| ~/app/playground/rhsi | session 2026-08-27 | CRC disk cleanup: crictl prune, journal vacuum, API log cleanup, completed pod deletion |
Prerequisites
crcstartandcrcstopwrapper scripts installed in~/.local/bin/(use thecrc-cmdskill to install them)- CRC installed and configured with libvirt driver
virshavailable (fromlibvirt-clientpackage)- SSH accessible into CRC VM on
127.0.0.1:2222(for cleanup operations)
Starting the Cluster
Follow these steps in order when starting CRC:
1. Show CRC version
Always run crc version first and show the output to the user:
crc version
This confirms which CRC and OpenShift versions are installed before attempting to start the cluster.
2. Start with crcstart
Use the wrapper script, never crc start:
crcstart
To pass additional arguments to the underlying crc start:
crcstart -- --log-level debug
What ships with it
2 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.
- 3d ago First seen · 266 lines · 26 tokens per session scan A 3e74ee2b2fc7
crc-ctl is a skill published in the GitHub repository rhtevan/agentfs (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 26 tokens to every session and 2,449 once invoked, about $0.0001 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
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
toolset-design
Design and validate new MCP toolsets, tools, and tool changes. Use when planning a new toolset, adding tools to an existing toolset, reviewing a toolset PR, or deciding whether a new tool is warranted. Covers the full lifecycle: eval-first validation, tool design methodology, consolidation patterns, and review…
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.
nvca-values-customization
Customize NVCA Operator Helm chart values in the native monorepo. Use when modifying vendored defaults, changing stack-derived install values, adding deployment-time overrides, or updating scripts under deploy/helm/nvca-operator.
portainer-mcp-hygiene
How to drive the Portainer MCP server's tools correctly — both reading and mutating. Reading: project responses with select (JMESPath), where the heavy fields live (snapshots, status blocks, managed fields), how to handle non-JSON Docker/K8s proxy endpoints (container and pod logs, stats, exec), and how to interpret…
node-logs
Retrieve logs from a Kubernetes node — systemd units (journalctl) or files under /var/log. Use when you need node-level evidence: containerd, kubelet, kernel/OOM, or anything the pod's own log cannot show. Three access paths in order: hostscript (SSH), nodescript (debug pod), and localscript against the kubelet log…