nix-pr-review

nix-pr-review is a skill for Claude Code, Codex from shikanime-labs/skills. It costs 39 tokens per session (2,201 once invoked), scanned A, original, Apache-2.0.

A review procedure for pull requests in NixOS’s package collection, which is the codebase used to build and configure NixOS software.

In plain words
What is it for?
Use it to review nixpkgs pull requests, run the required package builds, inspect the diff, and report whether the changes are ready for maintainer approval.
Why use it?
It ensures changed packages are built and the proposed code follows the project’s contribution conventions before approval.

Skill for Claude CodeCodex

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

Good fit Use it to review nixpkgs pull requests, run the required package builds, inspect the diff, and report whether the changes are ready for maintainer approval.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shikanime-labs/skills/nix-pr-review
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 shikanime-labs/skills --skill nix-pr-review
Clone the repo
git clone --depth 1 https://github.com/shikanime-labs/skills

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 nix-pr-review

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/shikanime-labs/skills/nix-pr-review"><img src="https://agentmods.dev/badge/skills/shikanime-labs/skills/nix-pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,201 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 $0.00039 $0.02201
Opus 5 $0.00019 $0.01100
Sonnet 5 $0.00008 $0.00440
Haiku 4.5 $0.00004 $0.00220

Measured 12d ago against content hash 60dcf8c30b4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

nix-pr-review 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 12d 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.

skills/nixpkgs/nix-pr-review/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nixpkgs PR Review (nix-pr-review)

Review upstream NixOS/nixpkgs pull requests through the official contribution process: build every package the PR changes with nixpkgs-review, then check the diff against nixpkgs conventions before deciding on approval. Reports only — never auto-approve or merge without the maintainer's go-ahead.

This skill is grounded in a real modernization PR, NixOS/nixpkgs#557075 (ghstack: modernize), used below as the running example.

When to Use

  • "review this nixpkgs PR", "check PR #N on NixOS/nixpkgs", "is this package update good to merge"
  • Requested as a reviewer on an upstream nixpkgs PR
  • Any PR touching pkgs/, pkgs/by-name/, nixos/modules/, lib/, pkgs/test/, or nixos/tests/ in nixpkgs

Prerequisites

  • A full (non-shallow) local nixpkgs clone. Shallow clones miss merge bases and nixpkgs-review fails on them: git clone https://github.com/NixOS/nixpkgs (add --depth is NOT supported).
  • nix available (Lix or Nix ≥ 2.18). nixpkgs-review is packaged: nix run 'nixpkgs#nixpkgs-review' -- ... or nix shell nixpkgs#nixpkgs-review.
  • gh authenticated if posting the result as a PR comment.
  • Optional but recommended: nom (nix-output-monitor) for readable build logs; glow and delta for rendered markdown/diffs. Skipped silently if absent.

Quick Reference

cd ~/git/nixpkgs
nixpkgs-review pr <PR#>                # build changed packages, drop into shell
nixpkgs-review pr <PR#> --post-result  # build + post markdown result to the PR
nixpkgs-review pr <PR#> --print-result --no-shell
nixpkgs-review pr <PR#> --systems aarch64-linux
nixpkgs-review pr <PR#> --run 'cat report.json'
nixpkgs-review pr <PR#> --no-shell --post-result
nixpkgs-review rev HEAD                # review a local commit/branch
nixpkgs-review wip                     # review uncommitted working-tree changes
nixpkgs-review pr <PR#> --extra-nixpkgs-config '{ cudaSupport = true; }'

Read the full file on GitHub · 188 lines

Files

What ships with it

2 files 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. 12d ago First seen · 188 lines · 39 tokens per session scan A 60dcf8c30b4a

Subscribe to this mod's changes

nix-pr-review is a skill published in the GitHub repository shikanime-labs/skills (2 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 2,201 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 2026-08-31.

Related

Other skills, from other repositories

issue

Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…

jeremylongshore/tons-of-skills-marketplace · 115 tokens

swarm-pr-review

Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…

ZaxbyHub/opencode-swarm · 91 tokens

include-test-files-that-assert-on-behavior-being-changed-in-decl

When delegating a task affected by this skill, include.

ZaxbyHub/opencode-swarm · 29 tokens

review

Use when the user wants code assessed rather than changed — "review PR 88", "is this branch ready to merge?", "look over my changes", "any problems with this diff?", "give me a code review", "what do you think of this PR?", "sanity-check this branch", "ship it?". Applies to a pull request or the current branch when…

The01Geek/prflow · 123 tokens

magpie-pairing-self-review

Run a structured pre-flight self-review on local changes before opening a PR. Reads the diff against a configurable base (default: the merge base of HEAD and the upstream default branch), checks correctness, security, and project conventions, and returns a structured report to the developer. No state changes, no PR…

apache/magpie · 82 tokens

techdebt

Analyze Elixir/Phoenix technical debt — duplicates, refactoring opportunities, credo issues. Use when asked about code quality, cleanup, or what to improve.

oliver-kriska/claude-elixir-phoenix · 36 tokens