pr-review-cycle-retro

pr-review-cycle-retro is a skill for Claude Code, Codex from victorGPT/vibeusage. It costs 33 tokens per session (1,198 once invoked), scanned A, original, MIT.

A retrospective workflow for finding why a GitHub pull request needed repeated Codex reviews. It traces review comments to later code changes or follow-up fixes, then groups the causes by development stage.

In plain words
What is it for?
Use it when the same Codex feedback keeps returning, several review cycles occur, or a follow-up fix is needed after merging.
Why use it?
It replaces vague explanations of review churn with evidence about whether the cause was design, implementation, testing, review packaging, or release work. This helps teams prevent the same pattern in future reviews.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/ops/pr-retro.cjs \.

Good fit Use it when the same Codex feedback keeps returning, several review cycles occur, or a follow-up fix is needed after merging.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/victorGPT/vibeusage
agentmods
npx agentmods add skills/victorgpt/vibeusage/pr-review-cycle-retro

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-review-cycle-retro

README.md
[![agentmods](https://agentmods.dev/badge/skills/victorgpt/vibeusage/pr-review-cycle-retro/github.svg)](https://agentmods.dev/skills/victorgpt/vibeusage/pr-review-cycle-retro)
Your own site
<a href="https://agentmods.dev/skills/victorgpt/vibeusage/pr-review-cycle-retro"><img src="https://agentmods.dev/badge/skills/victorgpt/vibeusage/pr-review-cycle-retro/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-review-cycle-retro

Your own site · 80×15
<a href="https://agentmods.dev/skills/victorgpt/vibeusage/pr-review-cycle-retro"><img src="https://agentmods.dev/badge/skills/victorgpt/vibeusage/pr-review-cycle-retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,198 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00033 $0.01198
Opus 5 $0.00016 $0.00599
Sonnet 5 $0.00007 $0.00240
Haiku 4.5 $0.00003 $0.00120

Measured 10d ago against content hash 86c48b2dd070, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pr-review-cycle-retro 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 10d 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/pr-review-cycle-retro/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Review Churn Analysis (PR Retrospective)

Overview

Explain why Codex Cloud review had to be re-run. Attribute causes to specific development stages, not just PR outcomes.

When to Use

  • Multiple @codex review cycles on the same PR.
  • The same feedback appears across successive Codex reviews.
  • Follow-up fix PRs exist shortly after merge.
  • You need stage-level causes (design / implementation / testing / review packaging / release).

When NOT to use:

  • Human-review-only churn.
  • Pure formatting or mechanical PRs.

Core Pattern

  1. Select: Find PRs with Codex review churn (comment -> code update -> Codex review).
  2. Isolate: Filter only Codex Cloud reviews and actionable feedback.
  3. Evidence: Collect a traceable chain (Codex feedback -> code change or follow-up fix).
  4. Classify: Assign primary + secondary stage causes.
  5. Abstract: Roll causes into a stable taxonomy.
  6. Aggregate: Summarize causes across frontend/backends.
  7. Prevent: Enforce the PR template risk-layer gate before any future @codex review.

Quick Reference

Item Rule
Codex cycle Codex review comment -> code update -> new Codex review
Evidence Codex comment + fix commit OR follow-up fix PR OR regression doc
Stage attribution design / implementation / testing / review packaging / release
Mixed PR record both frontend and backend impact
Noise guard if Codex comments are generic, mark low-signal
Risk-layer gate if any trigger matches, fill the addendum before @codex review

Stage Taxonomy (Definition)

  • Design: missing requirements, unclear acceptance criteria, privacy/exposure gaps, cross-endpoint invariants not specified.
  • Implementation: logic errors, incomplete edge cases, inconsistent ordering/aggregation.
  • Testing: missing regression/E2E/contract tests, no reproduction script.
  • Review Packaging: PR lacks context, spec, evidence, or minimal repro for Codex to review well.
  • Release/Integration: environment constraints (gateway, permissions, paths), deploy-time mismatches.

Read the full file on GitHub · 123 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. 10d ago First seen · 123 lines · 33 tokens per session scan A 86c48b2dd070

Subscribe to this mod's changes

pr-review-cycle-retro is a skill published in the GitHub repository victorGPT/vibeusage (131 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,198 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.