SourceControl

SourceControl is a skill for Claude Code from rsts-dev/claude-buddy-marketplace. It costs 52 tokens per session (537 once invoked), scanned A, original, MIT.

A Git workflow helper for recording code changes, managing branches, and opening pull requests. Git is the tool developers use to track changes, while a pull request is a proposed change for review.

In plain words
What is it for?
Use it to stage and commit changes, create branches, push work, and create pull requests. It supports conventional commits, a standard format for describing changes.
Why use it?
It removes repetitive Git steps and keeps commit messages and branches consistent. It can also follow project rules such as protected branches and automatic pushing when configured.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Part of the buddy plugin — 6 skills, 7 commands shipped together

Install

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.

agentmods
npx agentmods add skills/rsts-dev/claude-buddy-marketplace/sourcecontrol
Any agent
npx skills add rsts-dev/claude-buddy-marketplace --skill sourcecontrol
Clone the repo
git clone --depth 1 https://github.com/rsts-dev/claude-buddy-marketplace

Made for: Claude Code.

Or install buddy, the plugin that ships this one along with the rest of its 6 skills, 7 commands.

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 SourceControl

README.md
[![agentmods](https://agentmods.dev/badge/skills/rsts-dev/claude-buddy-marketplace/sourcecontrol.svg)](https://agentmods.dev/skills/rsts-dev/claude-buddy-marketplace/sourcecontrol)
Your own site
<a href="https://agentmods.dev/skills/rsts-dev/claude-buddy-marketplace/sourcecontrol"><img src="https://agentmods.dev/badge/skills/rsts-dev/claude-buddy-marketplace/sourcecontrol.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 537 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00052 $0.00537
Opus 5 $0.00026 $0.00269
Sonnet 5 $0.00010 $0.00107
Haiku 4.5 $0.00005 $0.00054

Measured 6d ago against content hash 2e3bd93adca7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

SourceControl 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.

plugins/buddy/skills/SourceControl/SKILL.md · 66 lines

What it actually says

SourceControl

Professional git workflow automation with conventional commits, mode-aware interaction, ticket reference parsing, and clean commit rules.

Customization

Before executing, check for user customizations at: ~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/SourceControl/

If this directory exists, load and apply any PREFERENCES.md configurations (commit templates, branch naming conventions, protected branches). If not, proceed with defaults.

Prerequisites

LifeOS must be installed. Check ~/.claude/LIFEOS/VERSION. If missing, inform user: "LifeOS is required. Run /setup:lifeos to install."

Workflow Routing

Workflow Trigger File
Commit "commit", default invocation, git changes Workflows/Commit.md
CreateBranch "branch", "create branch", spec folder ref Workflows/CreateBranch.md
CreatePR "PR", "pull request", "create PR" Workflows/CreatePR.md

Auto-Detection

Default invocation routes to Commit workflow.

Configuration

The skill reads configuration from .claude/hooks.json (config section) when available:

  • config.git.auto_push — Auto-push after commit
  • config.git.branch_protection — Protected branches list
  • config.git.conventional_commits — Enforce conventional format
  • config.git.sign_commits — GPG signing

Examples

Example 1: Simple commit

User: "/buddy:commit"
-> Detects changes, stages, generates conventional commit message
-> Uses AskUserQuestion for confirmation
-> Creates commit, offers to push

Example 2: Commit with ticket reference

User: "/buddy:commit SDO-123 --yes"
-> Auto-yes mode, stages all changes
-> Generates: "SDO-123: feat(auth): add JWT validation"
-> Commits and pushes automatically

Example 3: Create pull request

User: "/buddy:commit PR"
-> Routes to CreatePR workflow
-> Ensures changes committed, generates PR description
-> Creates PR via gh CLI, returns URL
Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 66 lines · 52 tokens per session scan A 2e3bd93adca7

Subscribe to this mod's changes

SourceControl is a skill published in the GitHub repository rsts-dev/claude-buddy-marketplace (17 stars, last pushed 15d ago), licensed MIT. It adds 52 tokens to every session and 537 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 2026-08-30.