SaferSkills independently audited new-branch (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
✓—All security checks passedNo findings in this category for the latest scan.pass
Supply chainscore 100 · 0 findings
✓—All supply chain checks passedNo findings in this category for the latest scan.pass
Maintenancescore 100 · 0 findings
✓—All maintenance checks passedNo findings in this category for the latest scan.pass
Transparencyscore 100 · 0 findings
✓—All transparency checks passedNo findings in this category for the latest scan.pass
Communityscore 100 · 0 findings
✓—All community checks passedNo findings in this category for the latest scan.pass
Every scanned point with the score it earned and what moved between them.
1 scans · 90 days
c73d40f
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
skills/new-branch/SKILL.md · 1 file
skills/new-branch/SKILL.md0.8 KB · Markdown
name: new-branch
description: Create and switch to a new conventional-commit and semver-compliant branch before doing any work, then present the full execution plan for that branch and its pull request. Use when the user wants a branch prepared first and a clear plan in chat before implementation.
New Branch
Before any other work, inspect the current branch/worktree state.
Create and checkout a new branch for the task using a conventional-commit and semver-compliant name, keeping it short and scoped, for example feat/add-x, fix/y, or chore/z.
Stop after switching to the new branch unless the user separately asks for implementation work.
In chat, provide the complete plan for work to be done on that branch and its pull request: intended changes, key files, verification, commit shape, and any risks or blockers.