codex-pr-review-loop

codex-pr-review-loop is a skill for Claude Code, Codex from victorGPT/vibeusage. It costs 32 tokens per session (1,240 once invoked), scanned A, original, MIT.

A workflow for managing repeated Codex reviews of a GitHub pull request, including checks before submission and learning capture after merging. A pull request is a proposed code change awaiting review.

In plain words
What is it for?
Use it before or during a Codex-reviewed pull request to run risk checks, poll review comments, and capture causes of repeated review cycles.
Why use it?
It keeps review iterations organized and records why feedback led to more changes or another review. It also checks that important risks, edge cases, tests, and known gaps are documented.

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/victorgpt/vibeusage/codex-pr-review-loop
Any agent
npx skills add victorGPT/vibeusage --skill codex-pr-review-loop
Clone the repo
git clone --depth 1 https://github.com/victorGPT/vibeusage

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 codex-pr-review-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/victorgpt/vibeusage/codex-pr-review-loop.svg)](https://agentmods.dev/skills/victorgpt/vibeusage/codex-pr-review-loop)
Your own site
<a href="https://agentmods.dev/skills/victorgpt/vibeusage/codex-pr-review-loop"><img src="https://agentmods.dev/badge/skills/victorgpt/vibeusage/codex-pr-review-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,240 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 $0.00032 $0.01240
Opus 5 $0.00016 $0.00620
Sonnet 5 $0.00006 $0.00248
Haiku 4.5 $0.00003 $0.00124

Measured 4d ago against content hash 92faaa9c1636, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-pr-review-loop 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 4d 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.

docs/skills/codex-pr-review-loop/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex PR Review Loop

Overview

Run a 5-minute polling loop for PR review threads, but enforce a preflight Codex Context gate and capture post-merge learning when Codex churn occurs.

Workflow (Preflight + Loop + Post-Merge)

Preconditions

  1. If the user asks for preflight, run Step -1 before PR submission.
  2. If PR already exists, proceed to Step 0.
  3. gh is authenticated.
  4. You are allowed to push/merge as part of this explicit user-requested workflow.

Step -1: Pre-PR Codex Readiness (only when requested)

  • Open .github/PULL_REQUEST_TEMPLATE.md.
  • If any Risk Layer Trigger applies, fill the Risk Layer Addendum (rules/invariants, boundary matrix >= 3, evidence).
  • Ensure Codex Context lists delta, invariants, edge cases, tests, and known gaps.
  • Run the minimal regression tests that cover the boundary matrix.
  • Stop and ask the user to create the PR if it does not exist yet.

Step 0: Identify PR

  • Prefer current branch PR: gh pr view --json number.
  • If ambiguous, ask for PR number.

Step 1: Poll review threads, PR issue comments, and PR body reactions

Run:

GH_OWNER=<owner>
GH_REPO=<repo>
PR_NUMBER=<number>

gh api graphql -f owner="$GH_OWNER" -f name="$GH_REPO" -F number=$PR_NUMBER -f query='query($owner:String!,$name:String!,$number:Int!){repository(owner:$owner,name:$name){pullRequest(number:$number){reactionGroups{content users{totalCount}} reviewThreads(first:100){nodes{isResolved path line originalLine comments(first:50){nodes{author{login} body createdAt reactions(content: THUMBS_UP){totalCount}}}}} comments(first:100){nodes{author{login} body createdAt reactions(content: THUMBS_UP){totalCount}}}}}}}'

Step 2: Wait for updates (repeat until update)

  • Do not proceed unless review threads, PR issue comments, or PR body reactions have new updates since the last poll (new comments, new threads, updated timestamps, or reaction count changes).
  • If no updates are found, wait 5 minutes and poll again. Continue doing this automatically until updates appear.

Read the full file on GitHub · 110 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. 4d ago First seen · 110 lines · 32 tokens per session scan A 92faaa9c1636

Subscribe to this mod's changes

codex-pr-review-loop is a skill published in the GitHub repository victorGPT/vibeusage (131 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,240 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