What is create-pull-request?

A helper for preparing pull requests, which are proposed code changes submitted for review. It analyzes the current Git changes and drafts a localized title and description.

Selecting the target repository, reviewing branch or working-tree changes, drafting a pull-request title and body, and creating or updating the request after approval.

It helps turn a code diff into information reviewers can understand without manually reconstructing the change. It also checks which repository and changes should be used.

create-pull-request — Skill for Claude Code by atman-33/workhub

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 atman-33/workhub --skill create-pull-request

Clone the repo

git clone --depth 1 https://github.com/atman-33/workhub

Made for: Claude Code.

Or install engineering, the plugin that ships this one along with the rest of its 10 skills, 1 agent.

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/atman-33/workhub/create-pull-request/github.svg)](https://agentmods.dev/skills/atman-33/workhub/create-pull-request)

Your own site

<a href="https://agentmods.dev/skills/atman-33/workhub/create-pull-request"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/create-pull-request/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/atman-33/workhub/create-pull-request"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/create-pull-request.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 550 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	$0.00080	$0.00550
Opus 5.5	$0.00032	$0.00220
Sonnet 5.5	$0.00016	$0.00110
Haiku 4.5	$0.00008	$0.00055

Measured 1mo ago against content hash e8a5f77d51fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-pull-request 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 1mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/analyze_changes.mjs, scripts/generate_pr_body.mjs, scripts/quality_checks.mjs), 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/engineering/skills/create-pull-request/SKILL.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Pull Request

Creates reviewer-friendly PR drafts for a repository selected from the active workspace's registered projects.

Quick start

Pick the target repository using this order: a repository already resolved by a calling workflow; otherwise the repo named by the user; otherwise the repo owning the current file if it is unambiguous; otherwise a repository already surfaced in the current session's context (e.g. a registered-project list); otherwise ask one narrow question. Never assume a specific harness config file layout — it can change independently of this skill.
Run git and gh commands in the target repository root, not in the workspace working directory.
Save generated analysis and PR body files only under this skill's own .tmp/ directory (resolve this skill's actual base directory at runtime; never write into the workspace working directory or the target repository).
Draft first and ask for approval before creating or updating the PR, unless the user explicitly asked for immediate creation.

Workflow

Resolve the target repository path from the active context.
Use Push-Location / Pop-Location or an equivalent directory stack when switching into the target repository.
Run scripts/analyze_changes.mjs from the target repository to produce the analysis JSON.
Choose the PR template from assets/templates/ based on branch intent, then run scripts/generate_pr_body.mjs.
Run scripts/quality_checks.mjs before presenting or creating the PR.
Present the draft and warnings to the user, or create or update the PR immediately if the user explicitly asked for that fast path.

Guardrails

Never run git or gh against the workspace working directory (e.g. the workhub vault) unless the PR is intentionally for that repository itself.
Keep all temporary PR artifacts inside .tmp/ in this skill directory.
Treat a requested output language as binding for the final PR title and body.
Preserve issue references, but only emit closing keywords when the PR targets the repository default branch.
See REFERENCE.md for the full workflow, PowerShell examples, and error handling.

Read the full file on GitHub · 34 lines

Files

What ships with it

12 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.

1mo ago First seen · 34 lines · 80 tokens per session scan A e8a5f77d51fb

Subscribe to this mod's changes

create-pull-request is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 550 once invoked, about $0.0003 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 Code Git and workflow claude-code-plugin cross-platform desktop-app developer-tools obsidian

trellis-finish-work

Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.

fy-agent/fyagent · 46 tokens

pr-workflow

How to open a pull request that gets reviewed, and how to review one properly. Use when opening, describing, reviewing, updating or merging a PR.

Mikedev115/Aetox · 35 tokens

aetox-deploy

ก่อนปล่อยของและตอนเกิดเหตุ, checklist ก่อน deploy (migration, feature flag, rollback trigger, ยืนยัน CI), incident response (เกณฑ์ SEV1-4, สื่อสารระหว่างเหตุ, เขียน postmortem) และ git workflow ปลอดภัย (แยกงานด้วย worktree, ปิด branch ให้จบสะอาด) ทริกด้วย "จะ deploy", "production ล่ม", "ปิดงานยังไง".

Mikedev115/Aetox · 102 tokens

create-pull-request