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 agentmods add skills/realdougeubanks/claudemarketplace/git-workflownpx skills add RealDougEubanks/ClaudeMarketplace --skill git-workflowgit clone --depth 1 https://github.com/RealDougEubanks/ClaudeMarketplaceWrote 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/realdougeubanks/claudemarketplace/git-workflow)<a href="https://agentmods.dev/skills/realdougeubanks/claudemarketplace/git-workflow"><img src="https://agentmods.dev/badge/skills/realdougeubanks/claudemarketplace/git-workflow.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 | $0.00034 | $0.02864 |
| Opus 5 | $0.00017 | $0.01432 |
| Sonnet 5 | $0.00007 | $0.00573 |
| Haiku 4.5 | $0.00003 | $0.00286 |
Grade A, and why
git-workflow 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 5d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Workflow — Release-Branch Model
Enforce the release-branch Git model and help execute the correct git operations for your current context: start new work, open a PR, cut a release, or view the workflow reference.
Hard Rules (always enforced, no exceptions)
- Never commit or push directly to
main. If the current branch ismain, stop and create a new branch before making any changes. - Never force-push to
main. - All changes must reach
mainvia a PR from a release branch.
Instructions
When invoked, ask the user what they want to do (if not already specified):
"What would you like to do? (a) View the Git workflow reference (b) Start new work — scaffold a feature or fix branch (c) Open a PR for the current branch (d) Cut a release — merge release branch to main and tag (e) Resolve a merge conflict on the current branch (f) Manage stashes — list, view, apply, or drop stashes"
Then execute the appropriate action below.
Action (a) — View Workflow Reference
Print the full Git Workflow Reference section below.
Action (b) — Start New Work
-
Use Bash to identify the current release branch:
git branch -r | grep release | sort -V | tail -1No-release-branch fallback: If the command above returns no output (no
release/*branch exists), fall back to branching frommainand targetmainfor the PR. Inform the user:"No release branch found. Branching from
mainand the PR will targetmaindirectly. This is normal for simple repos and early-stage projects that do not yet use the release-branch model." In this case, replaceorigin/<release-branch>in step 4 withorigin/main, and use--base mainin thegh pr createcall in Action (c). -
Ask the user:
- Is this a new feature or a bug fix? (determines
feature/vsfix/prefix) - What is the task ID or short description? (e.g.
task-042,login-crash)
- Is this a new feature or a bug fix? (determines
-
Construct the branch name:
feature/task-XXX-short-descriptionorfix/task-XXX-short-description.
What ships with it
4 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.
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.
- 5d ago First seen · 299 lines · 34 tokens per session scan A 2ecd1c3c4838
git-workflow is a skill published in the GitHub repository RealDougEubanks/ClaudeMarketplace (1 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 2,864 once invoked, about $0.0002 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
release-notes
Draft a changelog for the next release by summarizing git commits since the last tag. Use only when the user asks to draft release notes, write a changelog entry, or prepare the next version's notes — never trigger automatically.
release-checklist
Generates a comprehensive pre-release validation checklist covering build verification, certification requirements, store metadata, and launch readiness.
changelog
Auto-generates a changelog from git commits, sprint data, and design documents. Produces both internal and player-facing versions.
swarm
Run a multi-agent audit of a codebase by spawning specialized parallel subagents (security, performance, tests, architecture, dead-code), then synthesize their findings into a single prioritized action plan. Use this whenever the user runs /swarm, asks to "audit the repo," "review this codebase," "find issues across…
tools-unity-behavior-designer
Behavior Designer patterns for AI behavior trees including task creation, shared variables, conditionals, and debugging.
tools-unity-flowcanvas
FlowCanvas visual scripting patterns for abilities, custom nodes, and graph execution.