pr-explainer

pr-explainer is a skill for Claude Code from imMamdouhaboammar/get-fable. It costs 19 tokens per session (721 once invoked), scanned A, original, MIT.

A tool for turning a pull request—the proposed code change submitted for review—into a self-contained web page explaining the change and its context.

In plain words
What is it for?
Use it to create walkthroughs for pull requests, release notes, and summaries of code changes.
Why use it?
It gives reviewers a readable overview before they inspect the code diff, including the problem, solution, alternatives, and reasons for the chosen approach. It clearly notes when the available information does not answer something.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the get-fable plugin — 78 skills, 1 agent, 5 hooks shipped together

Good fit Use it to create walkthroughs for pull requests, release notes, and summaries of code changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/immamdouhaboammar/get-fable/pr-explainer
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 imMamdouhaboammar/get-fable --skill pr-explainer
Clone the repo
git clone --depth 1 https://github.com/imMamdouhaboammar/get-fable

Made for: Claude Code.

Or install get-fable, the plugin that ships this one along with the rest of its 78 skills, 1 agent, 5 hooks.

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-explainer

README.md
[![agentmods](https://agentmods.dev/badge/skills/immamdouhaboammar/get-fable/pr-explainer/github.svg)](https://agentmods.dev/skills/immamdouhaboammar/get-fable/pr-explainer)
Your own site
<a href="https://agentmods.dev/skills/immamdouhaboammar/get-fable/pr-explainer"><img src="https://agentmods.dev/badge/skills/immamdouhaboammar/get-fable/pr-explainer/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-explainer

Your own site · 80×15
<a href="https://agentmods.dev/skills/immamdouhaboammar/get-fable/pr-explainer"><img src="https://agentmods.dev/badge/skills/immamdouhaboammar/get-fable/pr-explainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 721 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 $0.00019 $0.00721
Opus 5 $0.00010 $0.00360
Sonnet 5 $0.00004 $0.00144
Haiku 4.5 $0.00002 $0.00072

Measured 9d ago against content hash 1c23819c9587, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pr-explainer 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 9d 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.

assets/skills/claude-code/pr-explainer/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: pr-explainer
description: Generate a shareable walkthrough artifact for a pull request — what changed, why, and a reviewer-oriented before/after narrative.

No PR number was given — explain the current branch's pending PR:

  1. git log --oneline @{upstream}..HEAD for the commit list (fall back to origin/main..HEAD if no upstream)
  2. git diff @{upstream}...HEAD for the unified diff

Goal

Produce a shareable PR walkthrough artifact — a self-contained HTML page a
reviewer can read before opening the diff to understand what this change does,
why it's being made, and where to focus attention. Pitch the writing at a
reviewer seeing this PR for the first time.

Wherever the answers end up in the sections below, the page must answer all
five of these questions:

  1. What is the problem this PR is trying to solve?
  2. Why is it a problem?
  3. How are we solving it?
  4. What alternatives did we consider?
  5. Why is the current approach better than the alternatives?

If the diff, PR body, and commit messages give no evidence for one of these —
most often 4 and 5 — say that plainly (e.g. "the PR doesn't record what
alternatives were considered") instead of inventing an answer.

Build it from the explainer template

Load the artifact-explainer skill and build the page from its template,
publishing with the Artifact tool as that skill directs. Use the
template's sections flavor — keep the sections structure, delete the
numbered steps. Fill the slots as follows:

  • Lede — what this PR changes and why it's needed, in two or three
    sentences. If the PR body already says this well, reuse it.
  • Sections — lead with one architecture or flow diagram when the change
    has a structural story; otherwise skip straight to the code. Open with a
    before/after section showing the user-observable change (behavior, API
    shape, or output); skip it if the change has no observable surface. Then
    group the diff into sections cut at the material's joints — group related
    changes rather than splitting per file. In each section the code snippet is
    usually the subject matter itself: a trimmed snippet, a plain-language
    explanation, and anything a reviewer should look closely at; add a diagram
    only where structure or flow genuinely needs one (the skill's diagram-first
    default applies to concept explainers, not PR walkthroughs, which are
    mostly symbolic content). End with a section for what's not obvious from
    the diff — context the diff alone doesn't show (why this approach over an
    alternative, what was tried and rejected, follow-ups intentionally left
    out).
  • Recap — restate the takeaways as where a reviewer should focus

Read the full file on GitHub · 71 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. 9d ago First seen · 71 lines · 19 tokens per session scan A 1c23819c9587

Subscribe to this mod's changes

pr-explainer is a skill published in the GitHub repository imMamdouhaboammar/get-fable (3 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 721 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

omh-deploy-and-monitor

This is a Hermes-native deploy-and-monitor workflow skill.

rlaope/oh-my-hermes · 66 tokens

release-cut

Cut a new pi-agent-dashboard release: promote ## [Unreleased] in CHANGELOG.md, bump every workspace package.json per SemVer, commit, tag v , and push — triggering the Release workflow that publishes every non-private workspace, builds the Electron artifacts, and creates a GitHub Release. Use on "cut a release"…

BlackBeltTechnology/pi-agent-dashboard · 93 tokens

release-revoke

Revoke or rollback a pi-agent-dashboard release: delete the GitHub Release, remove the git tag locally and on origin, deprecate the npm version (npm unpublish is blocked after 72h), and optionally revert the release commit. Use when the user says "revoke release", "rollback release", "delete release", "unpublish…

BlackBeltTechnology/pi-agent-dashboard · 85 tokens

public-plugin-packaging

Use when packaging an Agentlas agent repo for public GitHub release, Codex plugin submission, Claude adapter distribution, or one-line terminal installation.

agentlas-ai/Agentlas-OS · 34 tokens

shipping-a-pr

Use when finished work needs to ship as a pull request, or when the ask is about a PR — creating one, bringing it up to date, adding screenshots, watching its checks, or addressing its review comments. Not for reviewing a PR you are not shipping.

JetBrains/thinkrail · 57 tokens

dev-git-workflow

Designs team Git workflows for branching, PRs, and releases. Use when choosing branching models, stacked PRs, merge queues, worktree isolation for agents, or collaboration rules.

vasilyu1983/AI-Agents-public · 43 tokens