nexu: Skill for Claude Code

.agents/skills/process-pr-reviews/SKILL.md

process-pr-reviews is a skill for Claude Code, Codex from nexu-io/nexu. It costs 93 tokens per session (2,345 once invoked), scanned A, original, MIT.

A workflow for finding and handling actionable inline review comments on a GitHub pull request. It treats CodeRabbit summaries and nitpicks separately from comments that point to a specific change.

In plain words
What is it for?
Use it to fetch, count, inspect, triage, resolve, or dismiss actionable CodeRabbit and Codex comments on a pull request.
Why use it?
It prevents review summaries, unrelated issue comments, and nitpicks from being mistaken for required fixes. This makes it easier to triage the feedback that actually needs a response or code change.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is nexu-io/nexu's own configuration. It tells Claude Code and Codex how to work on nexu itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nexu configures →

About the project

nexu is an open-source desktop client that connects an OpenClaw AI agent to messaging services such as WeChat, Feishu, Slack, and Discord. It is for people who want to chat with their agent from those channels using their own model credentials while keeping data on their computer, and the catalogue entries support its agent workflows.

nexu-io/nexu · 3,265 stars · on GitHub · nexu.io

Reuse

Borrowing it

Nothing to install: this file belongs to nexu-io/nexu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nexu-io/nexu/main/.agents/skills/process-pr-reviews/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nexu-io/nexu

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 process-pr-reviews

README.md
[![agentmods](https://agentmods.dev/badge/skills/nexu-io/nexu/process-pr-reviews/github.svg)](https://agentmods.dev/skills/nexu-io/nexu/process-pr-reviews)
Your own site
<a href="https://agentmods.dev/skills/nexu-io/nexu/process-pr-reviews"><img src="https://agentmods.dev/badge/skills/nexu-io/nexu/process-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 process-pr-reviews

Your own site · 80×15
<a href="https://agentmods.dev/skills/nexu-io/nexu/process-pr-reviews"><img src="https://agentmods.dev/badge/skills/nexu-io/nexu/process-pr-reviews.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,345 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 $0.00093 $0.02345
Opus 5 $0.00046 $0.01172
Sonnet 5 $0.00019 $0.00469
Haiku 4.5 $0.00009 $0.00234

Measured 10d ago against content hash d101da943ca4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

process-pr-reviews 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.

.agents/skills/process-pr-reviews/SKILL.md · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Process PR Reviews

This workflow supports both CodeRabbit and Codex PR review signals.

CodeRabbit Reviews

“Real review feedback” is strictly defined as:

  • inline review comments
  • not a review summary
  • not a nitpick

Nitpick comments from CodeRabbit must always be ignored to avoid unnecessary noise.

There is no need to analyze the comment content itself.

Data sources

The CodeRabbit workflow only needs these two sources:

  1. PR review comments

    gh api --paginate repos/<owner>/<repo>/pulls/<pr_number>/comments
    

    This is the authoritative source for real inline comments.

  2. PR reviews

    gh api --paginate repos/<owner>/<repo>/pulls/<pr_number>/reviews
    

    This is only used to identify and exclude review summaries / nitpick summaries. It is not used to extract the final result.

Do not treat these as primary sources:

  • gh pr view ...
  • gh api repos/<owner>/<repo>/issues/<pr_number>/comments

Reason: they are not the authoritative source for actionable inline comments.

Workflow

0. Optional: fetch review thread IDs early if resolve/dismiss may be needed

If the user may ask you to resolve review conversations after triaging them, fetch review thread IDs as soon as you know the PR number:

gh api graphql -f query='query { repository(owner: "<owner>", name: "<repo>") { pullRequest(number: <pr_number>) { reviewThreads(first: 100) { nodes { id isResolved comments(first: 20) { nodes { databaseId path line author { login } body } } } } } } }'

This is not a primary source for actionable review feedback. It is only for mapping inline comments to resolvable thread IDs.

Recommendation:

  • If the user only wants to view/list/count review feedback, this step is optional.
  • If the user may want to resolve conversations, doing this early is usually more convenient because you can map comment databaseId / path / line to thread IDs in one pass.
1. Fetch inline comments

Read the full file on GitHub · 282 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 · 282 lines · 93 tokens per session scan A d101da943ca4

Subscribe to this mod's changes

process-pr-reviews is a skill published in the GitHub repository nexu-io/nexu (3,265 stars, last pushed 4mo ago), licensed MIT. It adds 93 tokens to every session and 2,345 once invoked, about $0.0005 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.