validate-pr

A process for checking whether AI-generated pull-request review comments are supported by the actual code changes. A pull request is a proposed set of repository changes submitted for review before merging.

In plain words
What is it for?
Use it to validate review comments, identify hallucinated findings, rank issues by priority, and create an action list before merging a pull request.
Why use it?
It helps distinguish real problems from irrelevant comments or claims that the reviewer invented. Each comment is compared with the pull request’s actual diff, which is the line-by-line change list.

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

Made for: Claude Code, Codex.

Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,051 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 $0.00128 $0.01051
Opus 5 $0.00064 $0.00526
Sonnet 5 $0.00026 $0.00210
Haiku 4.5 $0.00013 $0.00105

Measured yesterday against content hash 2666169729b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate-pr 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 yesterday.

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/validate-pr/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validate PR Comments

Validate AI-generated PR review comments on a pull request — determine which are accurate, which are low-priority noise, and which are hallucinations — by cross-referencing every comment against the actual diff.

When to Apply

Reference these guidelines when:

  • The user wants AI/bot review comments on a PR checked for accuracy
  • Triaging which review feedback is worth addressing before merge
  • Separating genuine findings from hallucinations or misread intent
  • Producing a prioritized action list from a noisy automated review

Prerequisite: the gh CLI must be installed and authenticated.

Rule Categories by Priority

Priority Category Impact Prefix
1 Setup & Input CRITICAL setup-
2 Data Gathering CRITICAL fetch-
3 Validation CRITICAL validate-
4 Output HIGH output-

Quick Reference

1. Setup & Input (CRITICAL)

  • setup-gh-cli - Verify the gh CLI is installed and authenticated before anything else
  • setup-resolve-pr - Resolve the PR from the user's message (number/URL) or fall back to the current branch

2. Data Gathering (CRITICAL)

  • fetch-pr-data - Fetch comments, reviews, body, title, and files in one gh pr view --json call
  • fetch-complete-coverage - Also pull inline review-thread comments; review ALL of them, never a sample

3. Validation (CRITICAL)

  • validate-against-diff - Cross-reference each comment against the real diff and referenced files
  • validate-hallucination - Classify each comment: Valid / Low Priority / Hallucination / Addressed
  • validate-worth-addressing - Judge whether a technically-true comment is actually worth the change

4. Output (HIGH)

  • output-summary-table - Present a priority-sorted table with fixed assessment labels
  • output-followup-details - Expand a single item (comment ID, assessment, verdict) on request

Core Workflow

  1. Setup — Confirm gh is available and authenticated; resolve which PR to validate.
  2. Fetch — Pull all PR data plus inline review comments; count them so nothing is dropped.
  3. Validate — For each comment, cross-reference the diff, decide hallucination vs. valid, and weigh whether it is worth addressing.
  4. Report — Emit the priority-sorted summary table, then expand any item the user asks about.

Read the full file on GitHub · 102 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. yesterday First seen · 102 lines · 128 tokens per session scan A 2666169729b9

Subscribe to this mod's changes

validate-pr is a skill published in the GitHub repository arraydude/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 128 tokens to every session and 1,051 once invoked, about $0.0006 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

systematic-debugging

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

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens