CodeRabbit Rules from PR Reviews - Fetch Comments

CodeRabbit Rules from PR Reviews - Fetch Comments is a skill for Claude Code, Codex from wangke19/gemini-ai-helpers. It costs 26 tokens per session (1,145 once invoked), scanned A, original, Apache-2.0.

A data-collection workflow that retrieves human review comments from recently merged GitHub pull requests and returns cleaned JSON for analysis.

In plain words
What is it for?
Collecting review comments from a repository to identify recurring feedback and turn it into coding rules.
Why use it?
It removes bot messages, irrelevant noise, pagination work, and manual GitHub API calls when studying review feedback.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Collecting review comments from a repository to identify recurring feedback and turn it into coding rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wangke19/gemini-ai-helpers/coderabbit-rules-from-pr-reviews
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.

Any agent
npx skills add wangke19/gemini-ai-helpers --skill coderabbit-rules-from-pr-reviews
Clone the repo
git clone --depth 1 https://github.com/wangke19/gemini-ai-helpers

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 CodeRabbit Rules from PR Reviews - Fetch Comments

README.md
[![agentmods](https://agentmods.dev/badge/skills/wangke19/gemini-ai-helpers/coderabbit-rules-from-pr-reviews/github.svg)](https://agentmods.dev/skills/wangke19/gemini-ai-helpers/coderabbit-rules-from-pr-reviews)
Your own site
<a href="https://agentmods.dev/skills/wangke19/gemini-ai-helpers/coderabbit-rules-from-pr-reviews"><img src="https://agentmods.dev/badge/skills/wangke19/gemini-ai-helpers/coderabbit-rules-from-pr-reviews/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 CodeRabbit Rules from PR Reviews - Fetch Comments

Your own site · 80×15
<a href="https://agentmods.dev/skills/wangke19/gemini-ai-helpers/coderabbit-rules-from-pr-reviews"><img src="https://agentmods.dev/badge/skills/wangke19/gemini-ai-helpers/coderabbit-rules-from-pr-reviews.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,145 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.
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 $0.00026 $0.01145
Opus 5 $0.00013 $0.00573
Sonnet 5 $0.00005 $0.00229
Haiku 4.5 $0.00003 $0.00114

Measured 7d ago against content hash 6cfb7781542c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

CodeRabbit Rules from PR Reviews - Fetch Comments 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (fetch_pr_comments.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

extensions/teams/skills/coderabbit-rules-from-pr-reviews/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeRabbit Rules from PR Reviews - Fetch Comments

This skill runs a Python script that fetches human review comments from recent merged PRs in a given GitHub repository. It handles all GitHub API calls, bot filtering, noise removal, rate limiting, and pagination, returning clean JSON output for AI analysis.

When to Use This Skill

Use this skill as Step 2-3 of the /teams:coderabbit-rules-from-pr-reviews command to collect review comments. The script replaces manual gh api calls with a single Python invocation.

Prerequisites

  1. GitHub CLI (gh): Must be installed and authenticated.
  2. Python 3: Python 3.6 or later.

Script Location

extensions/teams/skills/coderabbit-rules-from-pr-reviews/fetch_pr_comments.py

Usage

# Default: 30 most recent merged PRs
python3 extensions/teams/skills/coderabbit-rules-from-pr-reviews/fetch_pr_comments.py openshift/origin

# Custom count
python3 extensions/teams/skills/coderabbit-rules-from-pr-reviews/fetch_pr_comments.py openshift/origin --count 50

# Full URL
python3 extensions/teams/skills/coderabbit-rules-from-pr-reviews/fetch_pr_comments.py https://github.com/openshift/origin

What the Script Does

  1. Parses the repo argument — accepts owner/repo or full GitHub URL
  2. Fetches recent merged PRs via gh pr list
  3. For each PR, fetches two types of comments:
    • Inline code review comments (/pulls/{number}/comments)
    • General discussion comments (/issues/{number}/comments)
  4. Filters out noise:
    • Bot accounts: logins ending in [bot] or matching known bots (coderabbitai, openshift-ci, openshift-bot, openshift-merge-robot, codecov, dependabot, renovate, k8s-ci-robot, etc.)
    • Prow commands: comments where every line starts with /
    • Approvals: /lgtm, /approve, /hold, etc.
    • Short comments: less than 20 characters
  5. Rate limiting: 0.5s sleep between API calls, with retry logic for rate limit errors

Output Format

Read the full file on GitHub · 122 lines

Files

What ships with it

1 file 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. 7d ago First seen · 122 lines · 26 tokens per session scan A 6cfb7781542c

Subscribe to this mod's changes

CodeRabbit Rules from PR Reviews - Fetch Comments is a skill published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,145 once invoked, about $0.0001 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 2026-09-03.