A guide to creating and reviewing pull requests, which are proposed code changes submitted for team review. It covers keeping changes focused, writing descriptions, and splitting large features into smaller requests.

Use it to prepare pull requests, write review descriptions, split large diffs, plan stacked pull requests, and document testing and screenshots.

It makes code review easier by reducing oversized or unclear changes. It also gives reviewers the context and test steps needed to assess a change.

pr — Skill for Claude Code by arbazkhan971

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 arbazkhan971/godmode --skill pr

Clone the repo

git clone --depth 1 https://github.com/arbazkhan971/godmode

Made for: Claude Code.

Or install godmode, the plugin that ships this one along with the rest of its 132 skills, 1 command, 7 agents, 3 MCP servers.

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/arbazkhan971/godmode/pr.svg)](https://agentmods.dev/skills/arbazkhan971/godmode/pr)

Your own site

<a href="https://agentmods.dev/skills/arbazkhan971/godmode/pr"><img src="https://agentmods.dev/badge/skills/arbazkhan971/godmode/pr.svg" alt="Measured on agentmods" height="20"></a>

Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 874 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.

Model	Per session	Once invoked
Fable 5.1	$0.00009	$0.00874
Opus 5	$0.00005	$0.00437
Sonnet 5	$0.00002	$0.00175
Haiku 4.5	$0.00001	$0.00087

Measured 3d ago against content hash 8bdbdfa7a4bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 3d 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/pr/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Activate When

/godmode:pr, "create a PR", "stacked PRs"
"PR template", "PR too large", "review request"
Large diff detected during /godmode:ship

Workflow

1. Assess PR Context

git diff --stat main...HEAD
git log --oneline main...HEAD

Branch: <name> | Base: <target> | Commits: <N>
Files: <N> | +<N>/-<N> lines
Size: XS(<50) | S(50-200) | M(200-400) | L(400-500) | XL(>500)

IF >500 lines: MUST split before review. IF >200 lines: recommend splitting.

2. PR Size Optimization

Splitting strategies:

By layer: data model -> logic -> API -> UI
By feature slice: each user-facing feature = 1 PR
By refactor+feat: refactor first, feature second
By test+impl: tests first, implementation second

3. PR Description Template

## Summary
<1-3 sentences: what and why>
## Problem
<Issue link: Closes #NNN>
## Solution
<How this PR solves the problem>
## Test Plan
<How to verify: automated + manual steps>
## Screenshots (if UI)

4. Stacked PRs for Large Features

main
  PR 1: data model (base: main)
    PR 2: service layer (base: PR 1)
      PR 3: API endpoints (base: PR 2)
        PR 4: UI (base: PR 3)

IF >5 PRs deep: use parallel branches instead. Max stack depth: 5.

5. Review Request Strategies

CODEOWNERS auto-assignment, round-robin rotation, domain expert tagging, buddy system. Assign 1-2 reviewers (never >3).

6. PR Metrics

Time to first review: target < 4 hours
Review rounds: target <= 2
Total cycle time: target < 24 hours
PR size (median): target < 200 lines
Approval rate (1st): target > 50%
Stale PR rate: target < 5%

IF high first-review time: set up CODEOWNERS + SLA. IF many rounds: self-review before requesting.

7. Commit

Create PR(s) with description template applied. "chore: PR workflow -- <strategy> for <feature>"

Hard Rules

NEVER create PR >500 lines without splitting.
NEVER leave PR description empty.
NEVER request review before self-reviewing diff.
NEVER force-push during active review.
NEVER assign >3 reviewers (1-2 ideal).
NEVER stack >5 PRs deep.
ALWAYS include issue/ticket link.
ALWAYS mark draft PRs as draft.
ALWAYS squash before merge (not during review).
NEVER merge with failing CI.

Read the full file on GitHub · 124 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.

3d ago First seen · 124 lines · 9 tokens per session scan A 8bdbdfa7a4bc

Subscribe to this mod's changes

pr is a skill published in the GitHub repository arbazkhan971/godmode (26 stars, last pushed 9d ago), licensed MIT. It adds 9 tokens to every session and 874 once invoked, about $0.0000 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 2026-09-03.

Code review Commits Git and workflow ai-agent ai-agents ai-code-review ai-skills automated-testing autonomous-coding

pr-workflow

Pull request lifecycle: commit, codex review, sync, review, fix, status, cleanup, and PR mining. Use when user wants to commit changes, get a second-opinion code review from Codex, push changes, create a PR, check PR status, fix review comments, clean up branches after merge, or mine tribal knowledge from PR reviews.…

notque/vexjoy-agent · 125 tokens

commit

Use when the user asks to commit changes (interactively, not inside an autonomous cycle). Runs code-simplifier + one reviewer (general code-reviewer OR the matching language reviewer, ECC agents/skills), then lint + targeted tests via evolve commit-gate run, writes a tree-SHA-bound attestation, commits + pushes via…

mickeyyaya/evolve-loop · 105 tokens

github

Manages all git operations (commit, push, branch management, PR creation) in a standardized, safe, and consistent way. Automatically runs the code-review skill before any commit. Enforces Conventional Commits standard. Handles the full lifecycle: branch → review → commit → push → PR.

omergocmen/vibe-coder-kit · 60 tokens

pr