create-pr-description

create-pr-description is a skill for Claude Code from tomzx/agents. It costs 28 tokens per session (1,002 once invoked), scanned A, original, MIT.

A structured pull-request description generated from the changes on the current Git branch. It can also compare the changes with a GitHub issue when one is supplied.

In plain words
What is it for?
Summarizing branch changes, describing what was implemented, and assessing how well a GitHub issue is addressed.
Why use it?
It turns a code diff into a review-ready explanation and checks whether the linked issue's acceptance criteria are covered.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

Good fit Summarizing branch changes, describing what was implemented, and assessing how well a GitHub issue is addressed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomzx/agents/create-pr-description
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 tomzx/agents --skill create-pr-description
Clone the repo
git clone --depth 1 https://github.com/tomzx/agents

Made for: Claude Code.

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 create-pr-description

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomzx/agents/create-pr-description/github.svg)](https://agentmods.dev/skills/tomzx/agents/create-pr-description)
Your own site
<a href="https://agentmods.dev/skills/tomzx/agents/create-pr-description"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-pr-description/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 create-pr-description

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomzx/agents/create-pr-description"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-pr-description.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,002 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 $0.00028 $0.01002
Opus 5.5 $0.00011 $0.00401
Sonnet 5.5 $0.00006 $0.00200
Haiku 4.5 $0.00003 $0.00100

Measured 22d ago against content hash 9967280d3cbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-pr-description 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/create-pr-description/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate PR Description

Generates a structured PR description from the current branch's diff against its PR base branch, optionally cross-referencing a GitHub issue to assess acceptance criteria coverage.

Prerequisites

  • gh CLI authenticated
  • ghx CLI authenticated (preferred for reading issue details)
  • An open PR must exist for the current branch (the diff target is the PR's base branch)
  • Current branch must have commits relative to its parent

Note: This skill diffs against the PR base branch reported by gh. For a workflow that diffs against the git merge base and creates the PR directly, use /create-pr instead.

Skill attribution (GitHub)

Before returning the PR description, read github-post-attribution/SKILL.md and append the Generated with footer for SKILL_DIR = create-pr-description to the end of the description body. This footer stays with the description when the user posts it to GitHub via gh pr create or gh pr edit.

Communication guidelines (outbound text)

Before composing any text posted or drafted on the user's behalf, apply communication-guidelines/SKILL.md.

Workflow

Compute diff (PR base -> HEAD)
        |
        v
Issue provided? ($1 $2)
   /         \
 Yes           No
  |             |
  v             v
Fetch issue   Skip issue
details       lookup
  |             |
  v             |
Assess          |
acceptance      |
criteria        |
  |             |
  +------+------+
         |
         v
Generate PR description markdown

Steps

  1. Compute the diff:
    git diff $(gh pr view --json baseRefName -q .baseRefName)..HEAD
    
  2. If $1 (repository) and $2 (issue number) are provided, fetch the issue:
    ghx issue view $2 --repo $1
    
  3. Resolve agents attribution per github-post-attribution/SKILL.md: compute SKILL_COMMIT, SKILL_SHORT_SHA, SKILL_FILE_URL, and {BASE} for SKILL_DIR = create-pr-description.
  4. Generate the PR description following the output format below, substituting the resolved SKILL_FILE_URL and SKILL_SHORT_SHA into the footer.
  5. Return the result inside a markdown code block with each sentence on its own line. Do not line wrap the description; each paragraph/bullet should be a single long line.

Read the full file on GitHub · 127 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. 22d ago Changed · +4 lines 9967280d3cbe
  2. 24d ago Changed e383d5b3b5c6
  3. 27d ago Changed · +1 lines b154d0fb5085
  4. 28d ago Changed · +4 lines 11b6dc2b5b07
  5. 1mo ago Changed e75504b84919
  6. 2mo ago First seen · 118 lines · 28 tokens per session scan A dbe06fdd6db3

Subscribe to this mod's changes

create-pr-description is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,002 once invoked, about $0.0001 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.