vastai-host-mcp: Skill for Claude Code

.github/skills/git/SKILL.md

git is a skill for Claude Code, Codex from Cogni-AI-OU/vastai-host-mcp. It costs 0 tokens per session (3,022 once invoked), scanned A, original, MIT.

A practical guide to using Git, the tool that records changes to code and manages different versions of a project. It focuses on safe, repeatable commands and clean commit history.

In plain words
What is it for?
Creating and amending commits, preparing fixup changes, handling shallow clones, working with hooks, and recovering safely from Git operations.
Why use it?
It helps avoid accidental data loss, unwanted prompts, messy merges, and inconsistent commits when working in a repository.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

This is Cogni-AI-OU/vastai-host-mcp's own configuration. It tells Claude Code and Codex how to work on vastai-host-mcp 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 vastai-host-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Cogni-AI-OU/vastai-host-mcp. 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/Cogni-AI-OU/vastai-host-mcp/main/.github/skills/git/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Cogni-AI-OU/vastai-host-mcp

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 git

README.md
[![agentmods](https://agentmods.dev/badge/skills/cogni-ai-ou/vastai-host-mcp/git/github.svg)](https://agentmods.dev/skills/cogni-ai-ou/vastai-host-mcp/git)
Your own site
<a href="https://agentmods.dev/skills/cogni-ai-ou/vastai-host-mcp/git"><img src="https://agentmods.dev/badge/skills/cogni-ai-ou/vastai-host-mcp/git/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 git

Your own site · 80×15
<a href="https://agentmods.dev/skills/cogni-ai-ou/vastai-host-mcp/git"><img src="https://agentmods.dev/badge/skills/cogni-ai-ou/vastai-host-mcp/git.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 3,022 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 $0.03022
Opus 5.5 $0.00000 $0.01209
Sonnet 5.5 $0.00000 $0.00604
Haiku 4.5 $0.00000 $0.00302

Measured 2mo ago against content hash f1299255a1f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git 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 2mo 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.

.github/skills/git/SKILL.md · 291 lines

How it starts

The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: git description: Guide for using git license: MIT

Expert in advanced git usage for repository agents. Prioritize non-interactive, safe, reproducible operations that maintain clean history and respect repository conventions.

Core Principles

  • Non-interactive execution: Commands must run without prompting. Never use interactive modes (-i, --interactive, default editors).
  • Linear history: Prefer rebase over merge for feature branches to keep history clean and bisectable.
  • Atomic changes: Favor small, focused commits. Use amend/fixup patterns for corrections.
  • Safety: Never perform destructive operations without explicit reasoning and user confirmation.
  • Hook handling: Aim to satisfy pre-commit/pre-push hooks. Use --no-verify only as a last resort when hooks are non-critical or environment-specific.
  • Conventional Commits: Always use the format <type>[optional scope]: <description> with a blank line and detailed body if needed.

Non-Interactive Patterns

  • Amending last commit (preserve author date): git commit --amend --no-edit --date="$(git log -1 --format=%aD)"
  • Fixup previous commits (non-interactive preparation):
    • Create fixup: git commit --fixup <commit-sha>
    • Later autosquash (requires interactive rebase-propose to user or defer to PR squash if agent cannot handle -i): git rebase -i --autosquash origin/main
  • Rebasing feature branches: git fetch origin && git rebase origin/main --no-verify (add --no-verify only if hooks block)
  • Cherry-picking without conflicts: git cherry-pick -x <commit-sha> (-x records original SHA for traceability)
  • Cherry-picking with editor bypass: GIT_EDITOR=true git cherry-pick --continue (auto-accept commit message during conflict resolution)
  • Stashing partial work (non-interactive): git stash push -m "wip-description" -- path/to/file (use pathspec for selective stashing; avoid -p as it is interactive)

Read the full file on GitHub · 291 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. 2mo ago First seen · 291 lines · 0 tokens per session scan A f1299255a1f4

Subscribe to this mod's changes

git is a skill published in the GitHub repository Cogni-AI-OU/vastai-host-mcp (0 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,022 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 2026-08-31.

Related

git compared with skills from other repositories

git next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gitCogni-AI-OU/vastai-host-mcpSkill029d agoMITA0Claude Code, Codex
merge-batchdiegosouzapw/OmniRouteSkill83k5d agoMITA46Claude Code
prowler-commitprowler-cloud/prowlerSkill15kyesterdayApache-2.0A44Claude Code, Codex
gh-auth-isolationgithub/gh-awSkill5.6kyesterdayMITA20Claude Code, Codex
github-skillzeenie-ai/OpenCompanySkill1.1kyesterdayMITA51Claude Code
comet-githubrpamis/cometSkill3.3kyesterdayMITA72Claude Code, Codex
release-helperSahir619/fable-methodSkill2.3k1mo agoMITA43Claude Code