Install
$ agentstack add skill-sniko-agent-skills-git ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
- if branch not created, create branch first before committing or opening PR
- if changes not committed, commit changes first before opening PR
Check for the followings for repository specific rules and instructions related to git names/messages conventions and workflows:
- AGETNS.md
- CLAUDE.md
- .agents/
Merge them with the general instructions below, with repository rules taking precedence in case of conflict.
Commit
Commit message format:
[scope]:
Rules
- One logical change per commit, if many files changed, create multiple commits with clear scope and messages
- Present tense: "add" not "added"
- Imperative mood: "fix bug" not "fixes bug"
- Reference issues:
Closes #123,Refs #456 - Keep description under 72 characters
- NEVER update git config
- NEVER run destructive commands (
--force, hard reset) without explicit request - NEVER skip hooks (
--no-verify) unless user asks - NEVER force push unless the user explicitly requests it
- NEVER commit to
master/mainunless repository rules allow it and the user confirms it
Branch
Branch naming format: {type}/{semantic-name}
Rules
- NEVER delete or rename existing branches without explicit user request
- NEVER force-push or reset master/main
- NEVER run destructive commands without confirmation
- If branch already exists, report this to the user and ask how to proceed
Pull Request
Title format: {type}[scope]: {description}
Description format:
## Summary
{1–3 sentences explaining what this PR does and its scope}
## Changes
- {key change 1, do not repeat file changes, focus on observable behavior changes}
- {key change 2, do not repeat file changes, focus on observable behavior changes}
- {more as needed — keep each bullet atomic and concrete}
## Why
{motivation: what problem does this solve, or what goal does it achieve.}
## Breaking Changes
{describe what breaks and how consumers should migrate. Omit if no breaking changes.}
Git workflows for branching, committing, and opening pull requests, with automatic convention detection and branch-safety checks.
Types
Change types:
| Type | Purpose | |---|---| | feat | New feature | | fix | Bug fix | | docs | Documentation only | | style | Formatting/style (no logic) | | refactor | Code refactor | | perf | Performance improvement | | test | Add/update tests | | build | Build system/dependencies | | ci | CI/config changes | | chore | Maintenance/misc |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: SNIKO
- Source: SNIKO/agent-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.