neo: Command for Claude Code

.claude/commands/gh-review-assess.md

gh-review-assess is a command for Claude Code from Parslee-ai/neo. It costs 93 tokens per session (15,446 once invoked), scanned A, original, Apache-2.0.

A command for assessing comments and reviews on GitHub pull requests, which are proposed code changes. It retrieves a review comment, separates valid engineering concerns from personal style preferences, and creates a practical plan for accepted issues.

In plain words
What is it for?
Use it with a GitHub review or comment URL to evaluate the feedback, explain why issues are accepted or rejected, and outline implementation work for the valid ones.
Why use it?
It helps decide which review feedback needs action instead of treating every suggestion as equally important. This reduces time spent on changes that do not improve the code.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

This is Parslee-ai/neo's own configuration. It tells Claude Code how to work on neo 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 neo configures →

Part of the neo plugin — 9 skills, 18 commands, 1 agent, 1 hook shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to Parslee-ai/neo. 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/Parslee-ai/neo/main/.claude/commands/gh-review-assess.md
Clone the repo
git clone --depth 1 https://github.com/Parslee-ai/neo

Made for: Claude Code.

Or install neo, the plugin that ships this one along with the rest of its 9 skills, 18 commands, 1 agent, 1 hook.

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 gh-review-assess

README.md
[![agentmods](https://agentmods.dev/badge/commands/parslee-ai/neo/gh-review-assess/github.svg)](https://agentmods.dev/commands/parslee-ai/neo/gh-review-assess)
Your own site
<a href="https://agentmods.dev/commands/parslee-ai/neo/gh-review-assess"><img src="https://agentmods.dev/badge/commands/parslee-ai/neo/gh-review-assess/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 gh-review-assess

Your own site · 80×15
<a href="https://agentmods.dev/commands/parslee-ai/neo/gh-review-assess"><img src="https://agentmods.dev/badge/commands/parslee-ai/neo/gh-review-assess.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 15,446 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 $0.00093 $0.15446
Opus 5 $0.00046 $0.07723
Sonnet 5 $0.00019 $0.03089
Haiku 4.5 $0.00009 $0.01545

Measured 12d ago against content hash 5c55e5a60851, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

gh-review-assess 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.

.claude/commands/gh-review-assess.md · 1,613 lines

How it starts

The opening of the file, as written. The whole thing — 1,613 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Usage

/gh-review-assess <comment_url>

Where:

  • comment_url (required): GitHub PR comment, review comment, or full review URL

Examples

Example 1: Basic Assessment of Single Comment

Scenario: You receive a code review comment suggesting that you refactor a working function to use a more "elegant" pattern. You want to assess whether this feedback is valuable or just stylistic preference.

Command:

/gh-review-assess https://github.com/acme/project/pull/456#issuecomment-789012

Expected Behavior:

  1. Fetches the comment content from GitHub using gh CLI
  2. Presents the comment to @agent-Linus for evaluation
  3. Linus categorizes the feedback as legitimate vs nitpicking
  4. For legitimate issues, @agent-linus-kernel-planner creates a simple implementation plan
  5. Returns structured summary showing accepted/rejected issues with rationale

Output:

REVIEW ASSESSMENT COMPLETE
=========================

Original Comment:
"This function should use map/reduce instead of a for loop. It's more functional."

LINUS EVALUATION:
Status: REJECTED
Category: Style Nitpicking
Rationale: The existing for loop is clear, performant, and maintainable.
Changing to map/reduce provides no tangible benefit and may reduce readability
for team members less familiar with functional patterns. This is textbook
bikeshedding.

VERDICT: No action required.

Notes:

  • If the comment contains multiple distinct issues, Linus will evaluate each separately
  • The command uses gh CLI's JSON API to fetch comment metadata and content
  • Authentication is required via gh auth login before first use
Example 2: Multi-Issue Review with Mixed Validity

Scenario: A reviewer posts a comment with five separate concerns. Some are valid security issues, others are stylistic preferences. You need to quickly determine which ones deserve attention.

Command:

/gh-review-assess https://github.com/acme/backend/pull/234#issuecomment-567890

Expected Behavior:

  1. Extracts all distinct issues from the comment
  2. Linus evaluates each issue independently
  3. Valid issues are passed to linus-kernel-planner
  4. Returns comprehensive breakdown showing decisions for each issue

Read the full file on GitHub · 1,613 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. 12d ago First seen · 1,613 lines · 93 tokens per session scan A 5c55e5a60851

Subscribe to this mod's changes

gh-review-assess is a command published in the GitHub repository Parslee-ai/neo (16 stars, last pushed 4d ago), licensed Apache-2.0. It adds 93 tokens to every session and 15,446 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.