agentmods.dev

git-create-pr

git-create-pr is a skill for Claude Code from mgiovani/cc-arsenal. It costs 105 tokens per session (1,465 once invoked), scanned A, original, MIT.

A workflow for creating a GitHub Pull Request, which asks a team to review proposed code changes. It uses the current branch’s commits and the repository’s pull-request template.

In plain words
What is it for?
Use it after committing and pushing work when you want to open a pull request for review.
Why use it?
It helps prepare a review request with details tied to the actual code changes. It also checks conditions such as a clean working tree before making repository changes.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents.

Part of the cc-arsenal-git plugin — 6 skills shipped together , and of cc-arsenal

not rated 8repo changed 22d ago A scan 105 tokens original MIT

Good fit Use it after committing and pushing work when you want to open a pull request for review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mgiovani/cc-arsenal/git-create-pr
View source ↗ mgiovani/cc-arsenal
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.

Any agent
npx skills add mgiovani/cc-arsenal --skill git-create-pr
Clone the repo
git clone --depth 1 https://github.com/mgiovani/cc-arsenal

Made for: Claude Code.

Or install cc-arsenal-git, the plugin that ships this one along with the rest of its 6 skills.

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 git-create-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/git-create-pr/github.svg)](https://agentmods.dev/skills/mgiovani/cc-arsenal/git-create-pr)
Your own site
<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/git-create-pr"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/git-create-pr/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for git-create-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/git-create-pr"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/git-create-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,465 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00105 $0.01465
Opus 5.5 $0.00042 $0.00586
Sonnet 5.5 $0.00021 $0.00293
Haiku 4.5 $0.00011 $0.00146

Measured 22d ago against content hash a3e0054324c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git-create-pr 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 22d 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.

skills/git-create-pr/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Pull Request

Create a GitHub Pull Request following conventional commits, pre-filled with the repo's PR template, and opened in the browser for final review.

Every PR bullet must map to an actual commit or diff hunk: drop claims you can't back with evidence in git log or git diff.

Invariant: never mutate the user's files to satisfy a precondition. If a check in step 1 fails, report it and stop. Do not run git checkout, git restore, git reset, git stash, or git clean against the user's tracked files to "fix" a dirty tree, and do not switch branches to route around a main/master check, those are the user's decisions, not this skill's. The only git commands this skill runs against the working tree are read-only until step 7's git push.

Workflow

  1. Validate preconditions (run this before anything else, including branch analysis)

    • Check working tree is clean: git status --porcelain. Any output means it's dirty.
      • If dirty: stop immediately. Show the git status --porcelain output and tell the user to commit or stash their changes first, e.g. Working tree has uncommitted changes: M README.md. Commit or stash before opening a PR. Do not proceed to step 2, and do not touch the listed files.
    • Requires gh (brew install gh): confirm gh auth status succeeds, else stop and tell the user to run gh auth login.
    • Get current branch: git branch --show-current.
      • If it's main or master: stop immediately. Tell the user there's no feature branch to open a PR from, e.g. Currently on main — check out a feature branch first. Do not proceed.
    • Check commits exist: git log origin/<base>..HEAD --oneline. If empty, stop and say there's nothing to open a PR for.
    • Extract ticket ID from branch name (e.g., ABC-123 from feature/ABC-123_description)

  2. Determine base branch

    • Use --base/-b argument if provided
    • Otherwise: gh repo view --json defaultBranchRef -q .defaultBranchRef.name
    • Fall back to main if detection fails

Read the full file on GitHub · 106 lines

Files

What ships with it

2 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. 22d ago Changed · -4 lines a3e0054324c9
  2. 1mo ago Changed · +1 lines 8169fbe82995
  3. 1mo ago First seen · 109 lines · 105 tokens per session scan A be59a954e96c

Subscribe to this mod's changes

git-create-pr is a skill published in the GitHub repository mgiovani/cc-arsenal (8 stars, last pushed 2d ago), licensed MIT. It adds 105 tokens to every session and 1,465 once invoked, about $0.0004 per session on Opus 5.5. 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.

Claude CodeGit and workflowagent-skillsagentskillsai-agentsautomationcli
Related

Other skills, from other repositories

gitlab

Agent-callable GitLab tools — manage issues and merge requests, review diffs, commit files, run pipelines, and search. Use when the user mentions GitLab or wants to review or merge an MR, commit code, run CI, or manage issues — even if they don't name GitLab explicitly.

zapier/connectors · 64 tokens

repo-hygiene

Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.

QwenLM/qwen-code · 48 tokens

gh-skill

Manage agent skills with gh skill. Use this skill to discover, preview, install, update, and publish Agent Skills so an agent can self-manage the skills available in its environment.

cli/cli · 41 tokens

cw-gates

Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.

Hmbown/Codewhale · 48 tokens

atmos-hooks

Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.

cloudposse/atmos · 46 tokens

conventional-commit

Conventional Commit - Generate Conventional Commits 1.0.0 compliant messages. MANDATORY for all git commits. Invoke when user says 'commit', 'commit this', or asks to commit code.

termio-sh/termio · 47 tokens