A workflow guide for managing Git branches and pull requests on GitHub, where pull requests are proposed code changes for review. It uses GitHub's command-line tool to create plans, submit changes, and organise related branches into stacks.

Use it to write branch plans, open or update pull requests, mark drafts ready, and create or maintain stacked branches. It also supports submitting, synchronising, restacking, viewing, and reviewing a stack.

It gives the agent a defined process for preparing, reviewing, synchronising, and merging changes across several branches. This reduces manual GitHub and Git commands and helps keep dependent pull requests in order.

pr-flow — Skill for Claude Code by izkreny: A workflow guide for managing Git branches and pull…

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/izkreny/agentifico/pr-flow

Any agent

npx skills add izkreny/agentifico --skill pr-flow

Clone the repo

git clone --depth 1 https://github.com/izkreny/agentifico

Made for: Claude Code.

Or install gh-solo, the plugin that ships this one along with the rest of its 4 skills, 1 agent, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/izkreny/agentifico/pr-flow.svg)](https://agentmods.dev/skills/izkreny/agentifico/pr-flow)

Your own site

<a href="https://agentmods.dev/skills/izkreny/agentifico/pr-flow"><img src="https://agentmods.dev/badge/skills/izkreny/agentifico/pr-flow.svg" alt="Measured on agentmods" height="20"></a>

Per session 236 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,495 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.

Model	Per session	Once invoked
Fable 5.1	$0.00236	$0.05495
Opus 5	$0.00118	$0.02747
Sonnet 5	$0.00047	$0.01099
Haiku 4.5	$0.00024	$0.00549

Measured today against content hash 650a2a53c6e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

pr-flow 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 today.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/docs-check.py, scripts/post-review.py, scripts/test-post-review.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/gh-solo/skills/pr-flow/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tools used: Bash(gh:*) for the extension, PR queries and review posting, Bash(git:*) for branch and worktree state, Read / Grep / Glob for repository context, Write / Edit for plan files and PR-body scratch files, Bash(python3:*) for scripts/docs-check.py, scripts/post-review.py and scripts/watch.py, Monitor / TaskStop for the watch in workflows/watch.md, Agent for the reviewer subagent that workflows/review.md spawns, Skill for entering the implement skill, which workflows/auto.md, workflows/review.md and workflows/discuss.md each do so the repository's own commands run under that skill's tool grant, EnterWorktree for moving the session into a sibling worktree in workflows/merge.md and workflows/stack.md.

The user invoked this skill with the argument: $ARGUMENTS

This is a routing skill. Read $ARGUMENTS and the conversation context, pick exactly one workflow, read that workflow file, and follow its instructions inline.

All paths below are relative to this skill's own directory. Resolve them against wherever this skill is installed rather than assuming a location.

Issue, ticket and task all mean the same thing: a GitHub issue. The tracker itself belongs to the tracker skill; this one starts where a branch does.

Every file here is written to the agent, so you is the agent reading it. The human is the owner, always in the third person. The distinction is load-bearing wherever authority is: a rule about who may approve a merge inverts if the referent slips. The exceptions are workflows/help.md, whose contents are printed to the owner, and README.md, which the owner reads rendered; both address them directly.

Who this is for

The owner owns the repository and is its only committer. Others may look — a mentor who comments, the reviewer agent a round spawns — but the owner is the only reviewer with authority: nobody else's approval gates a merge and nobody else is accountable for what ships. That is what makes workflows/review.md a round that prepares the owner's judgement rather than a substitute for it, and why REQUEST_CHANGES on their own PR is a note to themselves. If a second person commits to the repository, stop and say so: the confirmation gates and the assumption that a PR's author and its reviewer are the same person both stop making sense.

Read the full file on GitHub · 122 lines

Files

What ships with it

19 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.

today Changed · -21 lines 650a2a53c6e7
5d ago First seen · 143 lines · 236 tokens per session scan A 26bc30af153b

Subscribe to this mod's changes

pr-flow is a skill published in the GitHub repository izkreny/agentifico (2 stars, last pushed today), licensed MIT. It adds 236 tokens to every session and 5,495 once invoked, about $0.0012 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.

Code review Commits Git and workflow

create-pr

Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.

prisma/orm · 47 tokens

git-commit

Generate well-formatted git commit messages following conventional commit standards.

ThinkInAIXYZ/deepchat · 15 tokens

commit-push-pr

Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.

GCWing/BitFun · 68 tokens

mcore-split-pr

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

NVIDIA/skills · 25 tokens

commit

Commit current changes with a clear, descriptive message.

NVIDIA-NeMo/DataDesigner · 11 tokens

contributing

How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…

HugoRCD/evlog · 68 tokens