cosim-gpu: Skill for Claude Code

.agents/skills/cosim-gpu-disk-image-edit/SKILL.md

cosim-gpu-disk-image-edit is a skill for Claude Code, Codex from gevico/cosim-gpu. It costs 39 tokens per session (1,103 once invoked), scanned B, original, Apache-2.0.

A procedure for editing a running-system disk image without rebuilding the whole image. It can mount the image, change files and system services, and update kernel-module settings.

In plain words
What is it for?
Use it to add or replace guest files, add or update systemd services, change kernel-module configuration, or install ROCm debugging components.
Why use it?
It avoids a full image rebuild when only the guest system's files or configuration need to change. The image must not be in use by QEMU while it is mounted.

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 →

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-disk-image-edit/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-disk-image-edit

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/gevico/cosim-gpu/cosim-gpu-disk-image-edit"><img src="https://agentmods.dev/badge/skills/gevico/cosim-gpu/cosim-gpu-disk-image-edit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,103 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 $0.00039 $0.01103
Opus 5.5 $0.00016 $0.00441
Sonnet 5.5 $0.00008 $0.00221
Haiku 4.5 $0.00004 $0.00110

Measured 4d ago against content hash 9a9287f0c4cb, 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-disk-image-edit 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 4d 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.

- `guestmount` uses FUSE — no sudo needed
.agents/skills/cosim-gpu-disk-image-edit/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 Disk Image Edit

Modify a standalone copy of the vHost disk and launch it with an explicit kernel and disk configuration.

Prerequisites

  • Use a Linux host with guestmount, guestunmount, qemu-img and GNU coreutils.
  • Stop processes using the disk before mounting it. Keep the source recipe bundle idle while copying its kernel and disk.
  • Allow space for a standalone copy of the QCOW2 image (56 GB virtual capacity).
pgrep -af 'qemu-system-x86_64|cosim_launch.sh|run_cosim_tests.sh' && echo "STOP COSIM FIRST" || echo "OK"
command -v guestmount guestunmount qemu-img timeout tail

Prepare the editable image

Recipe bundles under build/images/ are verified build artifacts. Preserve their disk, kernel, manifest and verification records. A vhost.image selection verifies its bundle and rebuilds a modified artifact before launch.

Verify the source bundle, then create a standalone disk and matching kernel in a new directory under build/image-edits/. This directory is ignored by Git. Use a fresh directory for each edited image; the commands below reject an existing destination.

set -euo pipefail
SOURCE_BUNDLE="$PWD/build/images/ubuntu/24.04/x86_64/rocm/7.0"
CUSTOM_DIR="$PWD/build/image-edits/rocm70"
just ci-rocm-assets verify ubuntu/24.04/x86_64/rocm/7.0
test ! -e "$CUSTOM_DIR"
mkdir -p "$CUSTOM_DIR"
cp "$SOURCE_BUNDLE/kernel" "$CUSTOM_DIR/kernel"
qemu-img convert -f qcow2 -O qcow2 "$SOURCE_BUNDLE/disk" "$CUSTOM_DIR/disk.qcow2"

Keep the copied kernel paired with the disk's installed kernel modules. Changes to the kernel require exporting the corresponding boot artifacts as well.

Mount

DISK="$CUSTOM_DIR/disk.qcow2"
MOUNTPOINT="$CUSTOM_DIR/mount"
mkdir -p "$MOUNTPOINT"
guestmount -a "$DISK" -i --rw --pid-file "$CUSTOM_DIR/guestmount.pid" "$MOUNTPOINT"

Edit scope

Supported edit classes:

  • Add or replace files under the vHost filesystem.
  • Add or update systemd units and matching enablement symlinks.
  • Add or update kernel module configuration under /etc/modprobe.d/.
  • Install ROCm runtime debug components through repository scripts when the task is runtime debugging.
  • Inspect disk layout with qemu-img info "$DISK" if guestmount cannot inspect the image.

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. 4d ago Changed · +60 lines 9a9287f0c4cb
  2. 9d ago Changed e5aa21b6a97e
  3. 11d ago Changed · +1 tokens per session e91caf2d7980
  4. 12d ago Changed 5c22e5a5339d
  5. 19d ago First seen · 65 lines · 38 tokens per session scan B 4b715965cce6

Subscribe to this mod's changes

cosim-gpu-disk-image-edit is a skill published in the GitHub repository gevico/cosim-gpu (95 stars, last pushed 4d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,103 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens