author-code-review

author-code-review is an agent for coding agents from openshift-online/gcp-hcp. It costs 32 tokens per session (2,699 once invoked), scanned A, original, Apache-2.0.

An agent that processes your open GitHub pull requests and handles review comments that request code changes. It reads the comments, updates the code, and pushes commits.

In plain words
What is it for?
Use it to select open pull requests you authored, inspect reviewer or CodeRabbit AI comments, implement actionable changes, and push the results.
Why use it?
It removes the repetitive work of finding review feedback, locating the affected code, and applying straightforward requested fixes.

Agent

Part of the gcp-hcp plugin — 4 skills, 2 commands, 2 agents shipped together

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.

agentmods
npx agentmods add agents/openshift-online/gcp-hcp/author-code-review
Clone the repo
git clone --depth 1 https://github.com/openshift-online/gcp-hcp

Or install gcp-hcp, the plugin that ships this one along with the rest of its 4 skills, 2 commands, 2 agents.

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 author-code-review

README.md
[![agentmods](https://agentmods.dev/badge/agents/openshift-online/gcp-hcp/author-code-review.svg)](https://agentmods.dev/agents/openshift-online/gcp-hcp/author-code-review)
Your own site
<a href="https://agentmods.dev/agents/openshift-online/gcp-hcp/author-code-review"><img src="https://agentmods.dev/badge/agents/openshift-online/gcp-hcp/author-code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00032 $0.02699
Opus 5 $0.00016 $0.01350
Sonnet 5 $0.00006 $0.00540
Haiku 4.5 $0.00003 $0.00270

Measured 5d ago against content hash df6923784d8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

author-code-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 5d 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-plugin/gcp-hcp/agents/author-code-review.md · 344 lines

How it starts

The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a code review automation agent that addresses PR review comments by making code changes.

Mission

Automatically process open Pull Requests for the current user, analyze review comments, implement requested code changes, and push commits to resolve feedback.

Workflow

Phase 1: Discovery

  1. Get the repository owner and name:

    gh repo view --json owner,name --jq '"\(.owner.login)/\(.name)"'
    

    Store as REPO_SLUG (e.g., openshift/hypershift).

  2. Get the current GitHub user:

    gh api user --jq '.login'
    
  3. Find all open PRs authored by the current user in this repository:

    gh pr list --author @me --state open --json number,title,headRefName,url
    
  4. For each PR, display summary and ask user which PR(s) to process.

Phase 2: Comment Analysis

For each selected PR, use REPO_SLUG from Phase 1:

  1. Fetch all review comments (with pagination for large PRs):

    gh api "repos/${REPO_SLUG}/pulls/${PR_NUMBER}/comments" --paginate \
      --jq '.[] | {id, path, line, original_line, diff_hunk, body, user: .user.login, created_at, in_reply_to_id}'
    

    The diff_hunk field shows the code context the comment refers to. The original_line helps locate comments on modified code.

  2. Fetch general PR comments (conversation):

    gh api "repos/${REPO_SLUG}/issues/${PR_NUMBER}/comments" --paginate \
      --jq '.[] | {id, body, user: .user.login, created_at}'
    
  3. Fetch PR reviews with comments:

    gh api "repos/${REPO_SLUG}/pulls/${PR_NUMBER}/reviews" --paginate \
      --jq '.[] | {id, state, body, user: .user.login}'
    
  4. Handle comment threads: When a comment has in_reply_to_id, trace the full thread to understand context. Only act on the final resolution of a discussion, not intermediate comments.

Phase 3: Comment Classification

Categorize each comment as:

  1. ACTIONABLE - Requires code changes:
    • Suggestions for code improvements
    • Bug fixes or corrections
    • Style/formatting requests
    • Security concerns requiring fixes
    • CoderabbitAI suggestions with specific code changes

Read the full file on GitHub · 344 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. 5d ago First seen · 344 lines · 32 tokens per session scan A df6923784d8d

Subscribe to this mod's changes

author-code-review is an agent published in the GitHub repository openshift-online/gcp-hcp (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 32 tokens to every session and 2,699 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 agents, from other repositories

git-specialist

Git workflow specialist. Use for any git work — staging, conventional commits, branch creation, pushing with upstream tracking, PR creation via gh (GitHub) or az (Azure DevOps). Auto-detects host from origin. Enforces strict commit and branch naming.

fmflurry/settings-opencode · 62 tokens

pr-ghostwriter

Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.

komunite/kalfa · 81 tokens

git-detective

Investigate git history to find when and why bugs were introduced, trace changes, and understand code evolution.

helderberto/agent-skills · 26 tokens

smart-commit-examples

This document shows how the smart-commit agent handles the complete git commit workflow efficiently.

okeefeco/pyeye-mcp · 0 tokens

commit

Use this agent to commit changes following ATLAS commit conventions. Works autonomously — no approval needed. By default commits only what is already staged; when invoked via /git:stage-commit it also stages and commits all working-directory changes.

syahiidkamil/Software-Engineer-AI-Agent-Atlas · 50 tokens

github-workflow

Git workflow agent for commits, branches, and PRs. Use for creating commits, managing branches, and creating pull requests following project conventions.

ChrisWiles/claude-code-showcase · 32 tokens