git-pr-workflow

git-pr-workflow is a skill for Claude Code, Codex, Cursor from movahedan/monobun. It costs 68 tokens per session (2,299 once invoked), scanned A, original, MIT.

A Git and pull-request workflow for a project using Bun, the JavaScript runtime and package manager. It covers checking the working tree, choosing a branch, reviewing changes, committing, pushing, and preparing a pull request.

In plain words
What is it for?
Use it when finishing a branch, creating a conventional commit, running pre-commit checks, pushing changes, or writing a pull-request description from the repository template.
Why use it?
It reduces mistakes such as committing on the main branch, overlooking untracked files, or opening a pull request without the required project checks and context.

Skill for Claude CodeCodexCursor

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/movahedan/monobun/git-pr-workflow
Any agent
npx skills add movahedan/monobun --skill git-pr-workflow
Clone the repo
git clone --depth 1 https://github.com/movahedan/monobun

Made for: Claude Code, Codex, Cursor.

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-pr-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/movahedan/monobun/git-pr-workflow.svg)](https://agentmods.dev/skills/movahedan/monobun/git-pr-workflow)
Your own site
<a href="https://agentmods.dev/skills/movahedan/monobun/git-pr-workflow"><img src="https://agentmods.dev/badge/skills/movahedan/monobun/git-pr-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,299 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 $0.00068 $0.02299
Opus 5 $0.00034 $0.01149
Sonnet 5 $0.00014 $0.00460
Haiku 4.5 $0.00007 $0.00230

Measured 5d ago against content hash 9875f5014996, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-pr-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.

.cursor/skills/git-pr-workflow/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git + PR (monobun)

Prerequisite (phased initiatives): builder-workflow checkup PASS for this phase, then documentation-sync for the plan’s Documentation before PR list. Pipeline: initiative-workflow.

1. Verify

bun overall

2. Working tree

git status

Use this before branching to see what is modified, untracked, renamed, or deleted—enough to pick a branch prefix/slug and to spot unrelated changes that should stay out of the first commit.

3. Branch

Run after working tree observation and before staging so the first commit does not land on main and the branch name matches the actual change.

git branch --show-current

Before naming or validating the branch, read the full patch of what you are about to land (not --stat alone)—so the prefix/slug matches renames, deletes, and config churn, not a vague guess:

git diff HEAD

If the diff is huge, still scan paths, renames, deletes, and config keys (workflows, package.json, turbo.json, tools/scripts/, etc.). Fold untracked paths from git status (§2) into the same picture; they are not in git diff HEAD.

  • main — do not build a feature/fix commit stack here. Create and switch: git checkout -b <prefix>/<short-slug> (prefix + slug from the change; ask the user if the intent is ambiguous).
  • Any other branch — validate: bun run precommit -- --branch (add --quiet if you want no Ink UI). If it fails, move to a valid name: prefer git branch -m <prefix>/<short-slug> when the branch is not pushed yet; otherwise git checkout -b <prefix>/<short-slug> from the current tip so uncommitted work follows.

Shape: prefix/rest-of-name — first /-segment must be an allowed prefix (commit feat ≠ branch feature).

Name rules: length 1–100; only [a-zA-Z0-9\-_/.]; no doubled -, _, or /; no leading or trailing separator; main skips prefix rules.

Read the full file on GitHub · 170 lines

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. 5d ago First seen · 170 lines · 68 tokens per session scan A 9875f5014996

Subscribe to this mod's changes

git-pr-workflow is a skill published in the GitHub repository movahedan/monobun (18 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 2,299 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.