cosim-gpu: Skill for Claude Code

.agents/skills/cosim-gpu-guest/SKILL.md

cosim-gpu-guest is a skill for Claude Code, Codex from gevico/cosim-gpu. It costs 41 tokens per session (1,156 once invoked), scanned B, original, Apache-2.0.

A tool guide for interacting with a running Linux guest inside the cosimulation. It uses a console pipe to send commands and can inspect the guest, mount a shared folder, check GPU status, and load the driver manually.

In plain words
What is it for?
Use it to send commands to a running guest, read its console output, interrupt a command, inspect GPU and driver state, and work with the shared filesystem.
Why use it?
It avoids restarting the whole simulation when you need to inspect or change a live guest. It also provides the paths and checks needed to find the correct console session.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is gevico/cosim-gpu's own configuration. It tells Claude Code and Codex how to work on cosim-gpu itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cosim-gpu configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is printf '%s\n' "printf '%s\n' \"\${COSIM_GUEST_SUDO_PASSWORD:?set COSIM_GUEST_SUDO_PASSWORD}\" | sudo -S bash -lc 'cd /mnt/tests && ./build/vector_add'" > "$CONS.

Reuse

Borrowing it

Nothing to install: this file belongs to gevico/cosim-gpu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gevico/cosim-gpu/main/.agents/skills/cosim-gpu-guest/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/gevico/cosim-gpu

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for cosim-gpu-guest

README.md
[![agentmods](https://agentmods.dev/badge/skills/gevico/cosim-gpu/cosim-gpu-guest/github.svg)](https://agentmods.dev/skills/gevico/cosim-gpu/cosim-gpu-guest)
Your own site
<a href="https://agentmods.dev/skills/gevico/cosim-gpu/cosim-gpu-guest"><img src="https://agentmods.dev/badge/skills/gevico/cosim-gpu/cosim-gpu-guest/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.

agentmods 80×15 button for cosim-gpu-guest

Your own site · 80×15
<a href="https://agentmods.dev/skills/gevico/cosim-gpu/cosim-gpu-guest"><img src="https://agentmods.dev/badge/skills/gevico/cosim-gpu/cosim-gpu-guest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,156 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.01156
Opus 5.5 $0.00016 $0.00462
Sonnet 5.5 $0.00008 $0.00231
Haiku 4.5 $0.00004 $0.00116

Measured 11d ago against content hash 481cd4ee7f4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

cosim-gpu-guest 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 11d 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.

printf '%s\n' "printf '%s\n' \"\${COSIM_GUEST_SUDO_PASSWORD:?set COSIM_GUEST_SUDO_PASSWORD}\" | sudo -S bash -lc 'cd /mnt/tests && ./build/vector_add'" > "$CONSOLE_PIPE"
.agents/skills/cosim-gpu-guest/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cosim vHost

Interact with the cosim vHost Linux through a successful test session kept alive with just test-gpu --keep-alive <program>. A just run-launch session keeps the console attached to the terminal instead of creating a detached console pipe.

Prerequisites

The launcher or test runner prints the active console log and control pipe:

Console log: /path/to/qemu.log
Console pipe: /tmp/<session-name>-<run-id>.session/console.in

If those lines are unavailable, derive the paths from the run id and session name:

SESSION_NAME=qemu-cosim-tests
RUN_ID=<run-id>
CONSOLE_PIPE="/tmp/${SESSION_NAME}-${RUN_ID}.session/console.in"
CONSOLE_LOG="/tmp/${SESSION_NAME}-${RUN_ID}.log"
docker ps --filter name=gem5-cosim --format '{{.Names}}: {{.Status}}'
test -p "$CONSOLE_PIPE"
test -f "$CONSOLE_LOG"

Sending Commands

printf '%s\n' '<command>' > "$CONSOLE_PIPE"
printf '\003' > "$CONSOLE_PIPE"   # Ctrl-C
tail -n 80 "$CONSOLE_LOG"

Wait pattern:

baseline=$(wc -l < "$CONSOLE_LOG")
printf '%s\n' '<command>' > "$CONSOLE_PIPE"
while true; do
    current=$(wc -l < "$CONSOLE_LOG")
    if [[ "$current" -gt "$((baseline + 3))" ]]; then
        tail -20 "$CONSOLE_LOG"
        break
    fi
    sleep 2
done

Common operations

Mount 9p share

printf '%s\n' 'mount -t 9p -o trans=virtio,version=9p2000.L cosim_share /mnt' > "$CONSOLE_PIPE"

After mounting, paths under /mnt must resolve inside the shared tree. Host symlinks that point outside the shared repository will appear in the vHost but may resolve to an unmounted vHost path. If a script or artifact is missing through such a symlink, classify it as a vHost bridge path issue and rerun with a vHost-visible path before using the result as model evidence.

Do not assume any particular Host storage layout for artifacts. One developer may keep artifacts as a real directory, another may point it at a larger disk, and a CI worker may use a temporary workspace. Runner scripts that execute in the vHost should therefore use a configurable vHost-visible bridge path inside the shared tree, while final logs, matrices, verdicts, and provenance are still archived under the requested artifact directory. The transient bridge directory is not evidence by itself; preserve its script and output under the row artifact before cleanup.

Read the full file on GitHub · 125 lines

Changes

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.

  1. 11d ago Changed · +2 tokens per session 481cd4ee7f4c
  2. 12d ago Changed · +2 lines d41afd2e15cd
  3. 19d ago First seen · 123 lines · 39 tokens per session scan B 43e308a07c4d

Subscribe to this mod's changes

cosim-gpu-guest is a skill published in the GitHub repository gevico/cosim-gpu (95 stars, last pushed 4d ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,156 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-10.

Related

Other skills, from other repositories

gke-ai-troubleshooting-tpu-dynamic-slices-monitoring

Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…

google/skills · 107 tokens

gke-ai-troubleshooting-tpu-vbar-oom

Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…

google/skills · 125 tokens

doca-flow

DOCA Flow packet steering on NVIDIA NICs/DPUs, linked into a C application: match/action pipes, ports, representors, forwarding, hairpin, counters. Trigger on packet steering, classifier, rule-matching, representor, hairpin or 5-tuple-to-queue questions even when "DOCA Flow" is not named. Also covers pipe validation…

NVIDIA/skills · 224 tokens

competition-firmware-layout

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for firmware images, partition tables, boot chains, update packages, extracted filesystems, embedded configs, and device-facing trust boundaries. Use when the user asks to unpack firmware, map partition layout, inspect bootloader or init…

zhaoxuya520/reverse-skill · 110 tokens

diagnose-driver-install

Diagnose NVIDIA driver installation failures on DeepOps-managed nodes — nvidia-smi errors, "No devices were found", DKMS build failures, or GPU pods crash-looping. Use before reinstalling anything.

NVIDIA/deepops · 47 tokens

catc-troubleshoot

Catalyst Center troubleshooting workflows - device unreachable investigation, client connectivity issues, interface down analysis, site-wide outage triage, wireless roaming problems, integration with pyATS for CLI-level diagnostics. Use when the device is managed by Catalyst Center and you want its…

automateyournetwork/netclaw · 114 tokens