pr-explain

pr-explain is a skill for Claude Code, Codex from tomsej/pi-ext. It costs 36 tokens per session (744 once invoked), scanned A, original, MIT.

A written walkthrough of a GitHub pull request (PR), which is a proposed set of code changes for review. It explains the background, design idea, code path, evidence for claims, how to try the change, and includes a quiz.

In plain words
What is it for?
Use it to prepare a PR explanation or review guide from a PR number or URL. It reads the surrounding code and records the walkthrough as an English Markdown document.
Why use it?
It helps someone understand and review a PR without reading every file unaided, while checking the author's claims against the code, tests, and continuous-integration checks.

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/tomsej/pi-ext/pr-explain
Any agent
npx skills add tomsej/pi-ext --skill pr-explain
Clone the repo
git clone --depth 1 https://github.com/tomsej/pi-ext

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-explain

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomsej/pi-ext/pr-explain.svg)](https://agentmods.dev/skills/tomsej/pi-ext/pr-explain)
Your own site
<a href="https://agentmods.dev/skills/tomsej/pi-ext/pr-explain"><img src="https://agentmods.dev/badge/skills/tomsej/pi-ext/pr-explain.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 744 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 $0.00036 $0.00744
Opus 5 $0.00018 $0.00372
Sonnet 5 $0.00007 $0.00149
Haiku 4.5 $0.00004 $0.00074

Measured 3d ago against content hash de44547e511b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-explain 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 3d 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-explain/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Explain

Generate an accurate English explanation of one PR. Read the repository; never modify it.

Read the PR

Input: PR number or URL.

  • Metadata: gh pr view <n> --json title,body,baseRefName,headRefOid,url.
  • Changes and evidence: gh pr diff <n> and gh pr checks <n>.
  • Fetch without checkout: git fetch origin pull/<n>/head; inspect files with git show FETCH_HEAD:<path>.
  • Read callers and surrounding code, not only the diff.
  • Treat PR claims as claims: confirm each with code, tests, or CI; mark unsupported claims ⚠️.

Write the explanation

Save ~/Workspace/specs/<project>/pr-<n>-<slug>/explanation.md; derive project, number, and slug—never guess them. Use these sections in order:

  1. Background — optional newcomer context, then the specific problem.
  2. Intuition — the core idea with small example data.
  3. Change top to bottom — one causal architecture/code walkthrough.
  4. Claims and evidence — claim, user-visible result, exact test/check evidence.
  5. Try it yourself — disposable setup and observable checklist items - [ ].
  6. Quiz — five useful multiple-choice questions.

Change map

Use closed <details> blocks: <code>PRINCIPLE</code><code>FLOW</code><code>STEP</code><code>KEPT</code><code>VERIFY</code>. Each <summary> must stand alone: label, short title, one-sentence conclusion. Inside STEP, include only important files: 🟡 <a href="<diff-url>"><code>MODIFIED</code></a> or 🟢 <a href="<diff-url>"><code>NEW</code></a>. Make the file name a permalink to exact HEAD lines: .../blob/<sha>/<path>#Lx-Ly. Show a short final-code snippet fenced with the language of the source file; link to the diff instead of pasting raw diff headers. Skip lockfiles, generated files, mechanical edits, and repeated prose.

Format

Write Markdown only. Use small mermaid diagrams with example data; no ASCII diagrams. Use exact symbol, test, and file names. Unknown facts are or ⚠️, never inventions. Quiz answers must render inside raw HTML: <details><summary>Answer</summary><p><strong>B.</strong> Why it is right and the others are wrong.</p></details>. Print the absolute output path.

Read the full file on GitHub · 49 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. 3d ago First seen · 49 lines · 36 tokens per session scan A de44547e511b

Subscribe to this mod's changes

pr-explain is a skill published in the GitHub repository tomsej/pi-ext (69 stars, last pushed 16d ago), licensed MIT. It adds 36 tokens to every session and 744 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens