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 skills add saski/arnesto --skill new-repogit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/new-repo)<a href="https://agentmods.dev/skills/saski/arnesto/new-repo"><img src="https://agentmods.dev/badge/skills/saski/arnesto/new-repo/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.
<a href="https://agentmods.dev/skills/saski/arnesto/new-repo"><img src="https://agentmods.dev/badge/skills/saski/arnesto/new-repo.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00063 | $0.00694 |
| Opus 5 | $0.00032 | $0.00347 |
| Sonnet 5 | $0.00013 | $0.00139 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
new-repo 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 6d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
new-repo — create a repo for this project and push it
If the user seems unfamiliar with git, keep the vocabulary plain (the
share skill is this same flow in novice framing) — the mechanics below are
identical either way.
This skill creates Cursor-hosted repos. If the user explicitly asks for a different host, follow that request without using this skill.
1. Inspect the workspace first (always)
git rev-parse --is-inside-work-tree 2>/dev/null
git remote -v
- A remote already exists → this project already has a repo. Say which remote, offer to commit/push instead, and stop. Never create a second repo for a project that has one, and never change existing remotes.
- Not a git repository yet → you will
git initin step 2.
Default to a repo named after the project folder (lowercase, dashes; strip characters other than letters, digits, and dashes). Ask about the name only when it is genuinely ambiguous.
2. Prepare the project
Before staging anything, list what would be committed
(git status --porcelain or git ls-files -o --exclude-standard) and make
sure .gitignore covers dependency directories and secrets (.env*, key
and credential files). If anything that looks like a secret would be staged,
ask before including it — never stage-and-push blind.
git init -b main # only if not already a repo
git add -A && git commit -m "Initial commit" # only if nothing committed
3. Create and push the Cursor-hosted repo
If origin is missing, unauthenticated, or outdated, first invoke the
origin skill (synced at ~/.cursor/skills-cursor/origin/SKILL.md) for install +
sign-in, then:
origin repo create <name>
git remote add origin <clone URL printed by create>
git push -u origin main
origin repo create <name> needs no org prefix — the CLI resolves the
account's namespace. If the name is taken, pick a close variant (suffix a
word, not a number soup) and retry once; if it fails again, ask the user. On
a namespace or access error, follow the origin skill's recovery table.
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.
- 6d ago First seen · 75 lines · 63 tokens per session scan A 2d08d7daea09
new-repo is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed 4d ago), licensed Unlicense. It adds 63 tokens to every session and 694 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
git-ai-search
Search and restore AI conversation context from git history.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
gentle-ai-work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
machinist
Use Machinist to create, assign, monitor, and resume software tasks. Use when a coding agent needs to work with Machinist, its GitHub issue workflow, lifecycle labels, direct runs, or managed queue.
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".
repo-sentinel
Full security audit for public repositories across 12 attack surfaces: git history, secrets, CI/CD, containers, dependencies, licenses. Triggers on: "push to GitHub", "make repo public", "open source this", "is this safe to push", "release audit", "secret leaks".