pr-summary

pr-summary is a skill for Claude Code from divinevideo/divine-mobile. It costs 45 tokens per session (786 once invoked), scanned A, original, MPL-2.0.

A Git workflow helper that reads the changes on your current branch and turns them into a pull request description matching the project's template.

In plain words
What is it for?
It helps prepare ready-to-paste pull request bodies, identify related issue numbers, and summarize the type and main details of a change.
Why use it?
It removes the need to manually inspect commits and diffs or remember the required sections of the pull request template.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents).

Good fit It helps prepare ready-to-paste pull request bodies, identify related issue numbers, and summarize the type and main details of a change.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/divinevideo/divine-mobile/pr-summary
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 divinevideo/divine-mobile --skill pr-summary
Clone the repo
git clone --depth 1 https://github.com/divinevideo/divine-mobile

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 pr-summary

README.md
[![agentmods](https://agentmods.dev/badge/skills/divinevideo/divine-mobile/pr-summary/github.svg)](https://agentmods.dev/skills/divinevideo/divine-mobile/pr-summary)
Your own site
<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/pr-summary"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/pr-summary/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 pr-summary

Your own site · 80×15
<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/pr-summary"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/pr-summary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 786 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00045 $0.00786
Opus 5.5 $0.00018 $0.00314
Sonnet 5.5 $0.00009 $0.00157
Haiku 4.5 $0.00005 $0.00079

Measured 1mo ago against content hash 59f355800d37, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pr-summary 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.

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.

.agents/skills/pr-summary/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Summary Skill

Purpose

Generate a pull request description that follows the project's .github/pull_request_template.md format. Analyzes all changes on the current branch compared to main and produces a concise, ready-to-paste PR body.

Workflow

Step 1: Gather Context

# Current branch name
git branch --show-current

# Commits on this branch vs main
git log main..HEAD --oneline

# Files changed with stats
git diff main...HEAD --stat

# Full diff for analysis
git diff main...HEAD

Step 2: Detect Issue Number

Look for the related issue number from (in priority order):

  1. Argument passed to the skill
  2. Branch name (e.g., fix/explore-hashtags-empty-view -> search issues)
  3. Commit messages (e.g., Closes #1461)

Step 3: Analyze Changes

Read the diff and identify:

  • What the change does (1-3 sentences max)
  • Which type of change it is (bug fix, feature, refactor, etc.)
  • Key architectural decisions (layers affected, new files, patterns used)

Step 4: Output

Output the PR body as a raw markdown code block so the user can copy-paste it directly into the GitHub PR description field.

Wrap the entire output in a fenced code block with the markdown language tag:

```markdown
<the PR body here>
```

Output Template

The content inside the code block must follow this structure exactly:

## Description

[1-3 sentence summary of what changed and why]

**Related Issue:** Closes #[number]

## Type of Change

- [ ] New feature (non-breaking change which adds functionality)
- [ ] Bug fix (non-breaking change which fixes an issue)
- [ ] Breaking change (fix or feature that would cause existing functionality to change)
- [ ] Code refactor
- [ ] Build configuration change
- [ ] Documentation
- [ ] Chore

Only check the applicable type ([x]). Keep the description short and focused on the "what" and "why", not implementation details. Reviewers can read the diff for the "how".

Rules

  • Output as code block: Always wrap the full PR body in a ```markdown fenced code block so the user can copy-paste directly into GitHub.
  • Be concise: 1-3 sentences for description. No implementation details.
  • Follow the template exactly: Use the checkboxes from pull_request_template.md.
  • Single type: Only check one type of change unless it genuinely spans multiple.
  • Link the issue: Always include Closes #N if an issue is known.
  • No emoji in description: The template already has emoji in the type checkboxes.
  • No file lists or tables: The diff is available for reviewers. Don't duplicate it.

Read the full file on GitHub · 110 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. 1mo ago First seen · 110 lines · 45 tokens per session scan A 59f355800d37

Subscribe to this mod's changes

pr-summary is a skill published in the GitHub repository divinevideo/divine-mobile (264 stars, last pushed today), licensed MPL-2.0. It adds 45 tokens to every session and 786 once invoked, about $0.0002 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 2026-09-03.