cosim-gpu: Skill for Claude Code

.agents/skills/cosim-gpu-repo-maintenance/SKILL.md

cosim-gpu-repo-maintenance is a skill for Claude Code, Codex from gevico/cosim-gpu. It costs 0 tokens per session (818 once invoked), scanned A, original, Apache-2.0.

A repository-maintenance workflow for the cosim-gpu project that does not require running the simulation. It covers Git cleanup, submodule pointers, commit organization, ignore rules, author checks, and audits of agent instruction files.

In plain words
What is it for?
Use it to split local commits, update submodules, inspect staged changes, check sign-offs, update ignore rules, and validate skill-routing or instruction changes.
Why use it?
It separates routine repository hygiene from tasks that need build or simulation evidence. This helps avoid unnecessary test runs and keeps commits and generated files organized.

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-repo-maintenance/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-repo-maintenance

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/gevico/cosim-gpu/cosim-gpu-repo-maintenance"><img src="https://agentmods.dev/badge/skills/gevico/cosim-gpu/cosim-gpu-repo-maintenance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 818 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00818
Opus 5.5 $0.00000 $0.00327
Sonnet 5.5 $0.00000 $0.00164
Haiku 4.5 $0.00000 $0.00082

Measured 12d ago against content hash 2f0eddbc4ea9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cosim-gpu-repo-maintenance 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 12d 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.

.agents/skills/cosim-gpu-repo-maintenance/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cosim Repo Maintenance

Use this skill for repository hygiene in the cosim-gpu repository when the task does not need cosim build, launch, test, debug, review, or RLCR evidence.

Examples:

  • locate or update a submodule under third_party/, or edit the vendored .agents skill files
  • split a large local commit
  • rewrite local unpushed commits for better topic boundaries
  • audit skill files for sensitive literals or unwanted coupling
  • validate skill routing after skill instruction changes
  • inspect staged, unstaged, and untracked files before committing
  • keep logs, artifacts, build outputs, and scratch files out of history
  • verify commit author and Signed-off-by
  • update ignore rules for generated outputs

Do not use cosim-gpu-flow-plan for ordinary repository maintenance. If the task starts requiring cosim test evidence, switch to the matching cosim domain skill.

General Git Practice

These are general rules, not project-specific behavior:

  • Inspect before changing: git status --short, git diff --stat, git diff --cached --stat, and submodule status when relevant.
  • Keep commits topic-scoped and reviewable.
  • Do not include unrelated working-tree changes.
  • Do not rewrite commits that may already be shared unless the user explicitly asks.
  • Prefer path-limited git add and git commit over broad staging in a dirty tree.
  • Never use destructive checkout or reset commands to discard unknown changes without explicit user direction.

Project-Specific Rules

Read references/cosim-gpu-repo-policy.md before changing submodule pointers, editing skill files, or preparing project commits.

Maintenance Workflow

  1. Record repository state:

    git status --short
    git submodule status
    git diff --stat
    git diff --cached --stat
    
  2. Classify changes by owner:

    • top-level repository files, including vendored .agents skills
    • third_party/gem5 source submodule
    • third_party/gem5-resources resource submodule
    • third_party/qemu source submodule
    • generated artifacts or local scratch

Read the full file on GitHub · 99 lines

Files

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.

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. 12d ago Changed · +1 lines 2f0eddbc4ea9
  2. 19d ago First seen · 98 lines · 0 tokens per session scan A ef2aca3c3b40

Subscribe to this mod's changes

cosim-gpu-repo-maintenance is a skill published in the GitHub repository gevico/cosim-gpu (95 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 818 tokens. 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 2026-10-10.