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 pivoshenko/pivoshenko.ai --skill git-branch-creategit clone --depth 1 https://github.com/pivoshenko/pivoshenko.aiWrote 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/pivoshenko/pivoshenko.ai/git-branch-create)<a href="https://agentmods.dev/skills/pivoshenko/pivoshenko.ai/git-branch-create"><img src="https://agentmods.dev/badge/skills/pivoshenko/pivoshenko.ai/git-branch-create.svg" alt="Measured on agentmods" 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 | $0.00099 | $0.00767 |
| Opus 5 | $0.00049 | $0.00383 |
| Sonnet 5 | $0.00020 | $0.00153 |
| Haiku 4.5 | $0.00010 | $0.00077 |
Grade A, and why
git-branch-create 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 yesterday.
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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Branch
Make + checkout new branch. No confirm.
Flow
- Parallel:
git status+git branch --show-current. - Dirty tree -> stop. Tell user to stash or commit first. Why ->
checkout -bcarries staged + unstaged changes into the new branch silently, mixing them with future work. - Pick base:
- Detect, don't assume:
git symbolic-ref --short refs/remotes/origin/HEAD-> strip theorigin/. Ref missing (never fetched) ->git remote set-head origin -a, re-read. No remote ->main, fall backmaster. Why -> a repo based ondeveloportrunkgets branched off the wrong parent otherwise, and the mistake surfaces at PR time as a diff full of other people's commits. - On feature branch + user wants to branch off it -> use current. Skip step 4's fetch; go to step 5 "off current" variant.
- Detect, don't assume:
- Exists?
git show-ref --verify --quiet refs/heads/<name>-> 0 = stop, surface conflict, no overwrite. Why ->checkout -berrors anyway, but check early so message is clean + no half-state. - Create:
- Off
<base>(default):git fetch origin <base>+git checkout -b <name> origin/<base>. - Off current:
git checkout -b <name>(no fetch, no remote ref — current HEAD is the base).
- Off
- Print branch + base.
Naming
<type>/<short-kebab-desc> or <type>/<scope>-<short-kebab-desc>.
Whole name ≤ 60 chars.
Type
Same set + picks as git-commit. See that skill's Type pick + Tiebreakers for disambiguation. Quick list: feat|fix|perf|refactor|docs|test|build|ci|chore.
Desc
- kebab-case. Not camel / snake.
- Imperative present:
add,fix,remove. Notadded,fixes. - < ~50 chars, and keeps the whole name ≤ 60. Over -> drop the scope segment first, then cut modifiers, then pick a shorter verb. Never truncate mid-word:
feat/add-oauth-logreads like a different feature. - No ticket IDs unless asked. Why -> history readable + tool-agnostic; trackers come+go, branches stay. Asked -> suffix:
feat/add-auth-middleware-PROJ-123.
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.
- yesterday Changed · +2 lines f62bbc3754e8
- 6d ago First seen · 55 lines · 99 tokens per session scan A 0faf98d06c32
git-branch-create is a skill published in the GitHub repository pivoshenko/pivoshenko.ai (4 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 767 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
skill-upstream-pr
Improve an open-source GitHub skill and open a friendly suggestion PR upstream: fork, run skill-auto-improver, attach asm eval before/after metrics. Don't use for local-only skills, authoring from scratch, bulk repos, or registry publish.
80-livekit-agents-majiayu000-claude-skill-registr
Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter.
agent-creation-skill
Procedural guide for creating new agents from templates when project complexity requires delegation.
agent-creator
Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use…
agent-commit
Analyze changes and create a meaningful commit with agent authorship. Internal skill for evolveloop.
ac-commit-manager
Manage git commits for autonomous coding. Use when committing feature implementations, creating descriptive commits, managing git workflow, or handling version control.