pr-review

A pull-request and feature-branch review workflow for the microsoft/winappcli codebase. It examines the complete change and produces a human-readable decision about what matters.

In plain words
What is it for?
Use it to review a pull request, inspect a feature branch before submission, or repeat a review after fixing earlier findings.
Why use it?
It helps catch security, correctness, and other important problems before changes are pushed or merged. It also avoids treating a small code question as a full pull-request review.

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/microsoft/winappcli/pr-review
Any agent
npx skills add microsoft/winappCli --skill pr-review
Clone the repo
git clone --depth 1 https://github.com/microsoft/winappCli

Made for: Claude Code, Codex.

Per session 166 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,191 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 $0.00166 $0.02191
Opus 5 $0.00083 $0.01095
Sonnet 5 $0.00033 $0.00438
Haiku 4.5 $0.00017 $0.00219

Measured 2d ago against content hash a55d2389e363, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-review 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 2d 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.

.github/skills/pr-review/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the PR review orchestrator for microsoft/winappcli. Fan out parallel reviewers, run the branch for real, and hand back a human-readable decision with only the changes that actually matter.

Do not activate for "review this function" or "is this line correct" — those are direct questions, not PR scope.

1. Get the diff

Default to the branch: git --no-pager diff origin/main...HEAD. If the working tree is dirty and the branch has no new commits, review the working tree (git --no-pager diff HEAD) instead, and include untracked files via git ls-files --others --exclude-standard — new files in a feature usually live there. If both have substance, ask which the user wants. Honor an explicitly named scope or base ref over any of this.

Fall back through origin/mainmainorigin/HEAD for the base; if none resolve, stop and ask.

Capture the file list (--stat) and the full unified diff. 0 files → say so and stop. >50 files → warn and ask before proceeding.

Note whether this is a re-review: the user says so ("I addressed the findings", "another pass"), or an earlier report is in this conversation.

2. Fan out

Launch these in one response with the task tool, mode sync. Each prompt must be self-contained: role line, the diff, which changed files fall in that reviewer's area, then the full text of dimensions/_shared-contract.md and dimensions/<name>.md. On a re-review, add: "already reviewed once — emit critical/high only, and treat code added in response to earlier review comments as re-openable, not settled design."

Reviewer File
security dimensions/security.md
correctness & tests dimensions/correctness-and-tests.md
cli-ux dimensions/cli-ux.md
alternative-solution dimensions/alternative-solution.md
ship-surfaces dimensions/ship-surfaces.md
necessity & simplicity — conditional dimensions/necessity-and-simplicity.md

Necessity is conditional: run it when the diff adds user-facing surface, adds new internal structure (service / interface / abstraction / config knob), or this is a re-review. Skip it for small fixes, refactors, perf, docs, tests, and CI on a first review. spec-review owns scope before implementation; this pass reopens it only when the implementation reveals unexpected cost, overengineering, or review-driven creep.

Read the full file on GitHub · 192 lines

Files

What ships with it

8 files 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. 2d ago First seen · 192 lines · 166 tokens per session scan A a55d2389e363

Subscribe to this mod's changes

pr-review is a skill published in the GitHub repository microsoft/winappCli (1,205 stars, last pushed 4d ago), licensed MIT. It adds 166 tokens to every session and 2,191 once invoked, about $0.0008 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

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

heap-snapshot-analysis

Analyze V8 heap snapshots to investigate memory leaks and retention issues. Use when given .heapsnapshot files, asked to compare before/after snapshots, asked to find what retains objects, or investigating why objects survive GC. Provides snapshot parsing, comparison, retainer-path helpers, and scratchpad scripts.

microsoft/vscode · 65 tokens

integrated-browser

Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.

microsoft/vscode · 68 tokens

agent-host-e2e-tests

Use when writing, recording, updating, or troubleshooting the agent host end-to-end tests under src/vs/platform/agentHost/test/node/e2e (black-box tests that drive the whole agent host over the AHP protocol, using a CapiReplayProxy record/replay system for Claude/Copilot/Codex). Covers adding a cross-provider test…

microsoft/vscode · 104 tokens

agent-host-logs

Analyze Agent Host debug log exports. Use when given an ah-logs or ahp-logs zip/folder, an Export Agent Host Debug Logs bundle, events.jsonl, AHP JSONL transport logs, Agent Host.log, remote-agenthost.log, or copilot-logs.

microsoft/vscode · 62 tokens

launch

Launch Code OSS (VS Code from sources) into an isolated throwaway profile with unique debug ports so you can drive it with @playwright/cli AND attach a Node debugger via dap-cli in the same session. Use when working on VS Code itself and you want to interact with the running workbench, automate chat or UI flows, test…

microsoft/vscode · 96 tokens