pr-summarizer

pr-summarizer is a skill for Claude Code, Codex from chandrudp29/skillhub. It costs 42 tokens per session (801 once invoked), scanned A, original, MIT.

A guide for writing pull request descriptions from code changes or a list of commits. A pull request is a proposed change that others review before it is merged.

In plain words
What is it for?
Use it to document why a change exists, what it does, how it was tested, possible breakage, and follow-up work.
Why use it?
It explains the problem, approach, testing, risks, and limitations that a list of changed files does not show clearly.

Skill for Claude CodeCodex

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/chandrudp29/skillhub/pr-summarizer
Any agent
npx skills add chandrudp29/skillhub --skill pr-summarizer
Clone the repo
git clone --depth 1 https://github.com/chandrudp29/skillhub

Made for: Claude Code, Codex.

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-summarizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/chandrudp29/skillhub/pr-summarizer.svg)](https://agentmods.dev/skills/chandrudp29/skillhub/pr-summarizer)
Your own site
<a href="https://agentmods.dev/skills/chandrudp29/skillhub/pr-summarizer"><img src="https://agentmods.dev/badge/skills/chandrudp29/skillhub/pr-summarizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 801 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.00801
Opus 5 $0.00021 $0.00400
Sonnet 5 $0.00008 $0.00160
Haiku 4.5 $0.00004 $0.00080

Measured 5d ago against content hash 55276b0a559a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

pr-summarizer 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 5d 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-summarizer/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Summarizer

Writes PR descriptions that reviewers actually read — context-first, not diff-first.

When to Use

  • "Write a PR description for this"
  • "Summarize what these commits do"
  • "Help me document this change"
  • Before opening any non-trivial PR

What a Good PR Description Does

It answers the questions a reviewer has before they look at the diff:

  1. Why does this change exist? (the problem, not the solution)
  2. What did you change? (the approach, not every file)
  3. How do I know it works? (test plan, screenshots, benchmark)
  4. What should I watch out for? (risks, known limitations, follow-up needed)

A PR description is not a diff summary. "Changed X in file Y" is what git already shows. The PR description should explain what the reviewer cannot see from the diff.

Workflow

Step 1 — Read the diff and commits

Before writing anything, understand:

  • What problem does this solve? (if not obvious, ask)
  • What was the approach taken (and what alternatives were considered)?
  • What's the blast radius — what could break?
  • Are there any TODOs, hacks, or known limitations in the code?

Step 2 — Write the description

## What and Why

[1–3 sentences: the problem this solves and why it needed to be solved now.
Not "this PR adds X" — that's in the title. Why does X need to exist?]

## How

[The approach taken. Not every file changed — the mental model a reviewer 
needs to understand the diff. Include key design decisions and any 
alternatives considered and rejected.]

## Test Plan

- [ ] [Specific test: what you ran, what you verified]
- [ ] [Edge case tested]
- [ ] [Screenshot or link to demo if UI change]
- [ ] [Performance numbers if perf-sensitive change]

## Risks and Notes

[What could go wrong? What didn't you test? What follow-up is needed?
Leave blank if genuinely none — don't write "None" as a placeholder.]

Step 3 — Write the title

Format: [type]: [imperative verb] [what]

Types: feat, fix, refactor, perf, test, docs, chore

Read the full file on GitHub · 98 lines

Files

What ships with it

1 file 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.

  1. 5d ago First seen · 98 lines · 42 tokens per session scan A 55276b0a559a

Subscribe to this mod's changes

pr-summarizer is a skill published in the GitHub repository chandrudp29/skillhub (13 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 801 once invoked, about $0.0002 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 2026-08-30.