guide: Agent for Claude Code

.github/workflows/generate-ai-rules/agents/pr-review-resolver.md

pr-review-resolver is an agent for Claude Code from rios0rios0/guide. It costs 55 tokens per session (2,180 once invoked), scanned A, original, MIT.

An automated helper for resolving review comments on a GitHub pull request, which is a proposed set of code changes awaiting review. It examines unresolved discussions, applies valid changes, explains decisions, pushes updates and closes addressed threads.

In plain words
What is it for?
Use it with a pull request number or URL to evaluate review suggestions, implement accepted fixes, respond to comments and resolve completed threads.
Why use it?
It turns a list of review comments into tracked code changes and replies, reducing the need to handle each discussion manually.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

This is rios0rios0/guide's own configuration. It tells Claude Code how to work on guide 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 guide configures →

Part of the engineering-standards plugin — 5 skills, 8 commands, 7 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to rios0rios0/guide. 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/rios0rios0/guide/main/.github/workflows/generate-ai-rules/agents/pr-review-resolver.md
Clone the repo
git clone --depth 1 https://github.com/rios0rios0/guide

Made for: Claude Code.

Or install engineering-standards, the plugin that ships this one along with the rest of its 5 skills, 8 commands, 7 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 pr-review-resolver

README.md
[![agentmods](https://agentmods.dev/badge/agents/rios0rios0/guide/pr-review-resolver/github.svg)](https://agentmods.dev/agents/rios0rios0/guide/pr-review-resolver)
Your own site
<a href="https://agentmods.dev/agents/rios0rios0/guide/pr-review-resolver"><img src="https://agentmods.dev/badge/agents/rios0rios0/guide/pr-review-resolver/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 pr-review-resolver

Your own site · 80×15
<a href="https://agentmods.dev/agents/rios0rios0/guide/pr-review-resolver"><img src="https://agentmods.dev/badge/agents/rios0rios0/guide/pr-review-resolver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,180 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 $0.00055 $0.02180
Opus 5.5 $0.00022 $0.00872
Sonnet 5.5 $0.00011 $0.00436
Haiku 4.5 $0.00006 $0.00218

Measured 1mo ago against content hash cfcd78ca7a02, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pr-review-resolver 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 1mo 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.

.github/workflows/generate-ai-rules/agents/pr-review-resolver.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a PR review comment resolver. You fetch unresolved review threads from a GitHub pull request, analyze each comment, implement valid suggestions, reply explaining what was done (or why a suggestion was declined), push changes, and resolve addressed threads.

Input

The caller provides a PR number (e.g., 42) or a PR URL (e.g., https://github.com/owner/repo/pull/42). If a URL is provided, extract the PR number from it.

Procedure

Step 1 -- Detect repository context

gh repo view --json nameWithOwner -q '.nameWithOwner'

Split the result into {owner} and {repo}. Verify gh auth status succeeds before proceeding.

Step 2 -- Checkout the PR branch

gh pr checkout <PR_NUMBER>
git pull --rebase

This ensures the local working tree matches the latest state of the PR branch and that the branch tracks the remote.

Step 3 -- Fetch unresolved review threads

Use the GitHub GraphQL API to retrieve all unresolved threads:

gh api graphql -f query='
  query($owner: String!, $repo: String!, $pr: Int!) {
    repository(owner: $owner, name: $repo) {
      nameWithOwner
      pullRequest(number: $pr) {
        number
        reviewThreads(first: 100) {
          nodes {
            id
            isResolved
            comments(first: 10) {
              nodes {
                databaseId
                body
                path
                line
                startLine
                author { login }
              }
            }
          }
        }
      }
    }
  }
' -f owner="<OWNER>" -f repo="<REPO>" -F pr=<PR_NUMBER>

Filter to threads where isResolved is false. If no unresolved threads exist, report "No unresolved review threads found on PR #N." and stop.

Step 4 -- Process each unresolved thread

Sort threads by file path (alphabetical) so changes to the same file are grouped. For each thread:

4a. Understand the comment

Read the full conversation in the thread (all comments, not just the first). The last comment is usually the most relevant. Extract:

  • The file path and line number(s) referenced
  • The suggested change or concern
  • Whether it contains a GitHub suggestion block (```suggestion)

Read the full file on GitHub · 233 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. 1mo ago Changed · +9 lines cfcd78ca7a02
  2. 1mo ago First seen · 224 lines · 55 tokens per session scan A 8094e17e836c

Subscribe to this mod's changes

pr-review-resolver is an agent published in the GitHub repository rios0rios0/guide (4 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 2,180 once invoked, about $0.0002 per session on Opus 5.5. 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

harmonyos-app-resolver

HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.

affaan-m/ECC · 49 tokens

kotlin-reviewer

Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violations, and common Android pitfalls.

affaan-m/ECC · 38 tokens

security-reviewer

Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.

affaan-m/ECC · 52 tokens

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

cavecrew-reviewer

Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.

JuliusBrussee/caveman · 75 tokens

residue

Sweeps a scope for residue - the half of a refactor that never got deleted. Files nothing imports, files reachable only from their own tests, shims left at an old address, one concept living under two names, budgets whose slack stopped enforcing them, guards reading a baseline that no longer exists. Reports leads with…

langwatch/langwatch · 171 tokens