resolve-review

resolve-review is a command for Claude Code from sergeyklay/.agents. It costs 15 tokens per session (647 once invoked), scanned A, original, Apache-2.0.

A command for processing reviewer feedback from a GitHub pull request, chat, or pasted text. It uses the Babysit PR workflow to investigate comments and make justified code changes.

In plain words
What is it for?
Fetching pull-request comments, assessing suggestions, making targeted changes, and reporting how each comment was handled.
Why use it?
It gives review work a consistent process instead of handling comments ad hoc. It also produces a summary for the human reviewer.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions CLAUDE.md; installed under .agents/ (shared by several agents); mentions AGENTS.md.

Good fit Fetching pull-request comments, assessing suggestions, making targeted changes, and reporting how each comment was handled.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/sergeyklay/.agents/resolve-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.

Clone the repo
git clone --depth 1 https://github.com/sergeyklay/.agents

Made for: Claude Code.

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 resolve-review

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/sergeyklay/.agents/resolve-review"><img src="https://agentmods.dev/badge/commands/sergeyklay/.agents/resolve-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 647 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 $0.00015 $0.00647
Opus 5 $0.00008 $0.00324
Sonnet 5 $0.00003 $0.00129
Haiku 4.5 $0.00002 $0.00065

Measured 6d ago against content hash add5365a10ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

resolve-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 6d 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/commands/resolve-review.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your task is to resolve reviewer feedback on the current pull request or on comments the user provides inline.

Task

  • Use the babysit-pr Agent Skill to drive every step of the resolution: ingest, classify, run the Context7 evidence audit, apply changes surgically, and produce the human-only summary.
  • Detect the input mode automatically:
    • A GitHub PR number, URL, or the current branch's open PR → use the skill's GitHub-fetch flow.
    • Pasted text or inline reviewer comments → use them as-is.
  • Read the project's context files (AGENTS.md, CLAUDE.md, CONTRIBUTING.md, README.md), and project architecture documentation so you know the coding standards, verification commands, issue tracker.

Skill Enforcement

MANDATORY: Apply the babysit-pr Agent Skill verbatim.

The skill is the single source of truth for how to resolve reviewer comments. The project's context files are the source of truth for what counts as a valid standard, verification command, and Context7-required library. Consult each at the moment the skill calls for it.

Process:

  • Load the babysit-pr Agent Skill before reasoning about any comment.
  • Walk through each step in order - ingest, Context7 audit, classify, apply, verify, summarize. Do not reimplement, paraphrase, merge, or short-circuit any step. Every gate exists to prevent a documented failure mode.
  • If the skill is unavailable in this environment, stop and report the failure. Do not improvise a replacement protocol.
  • Emit the Step 6 summary directly in the chat response. The audience is the human operator, not a persistent file.

Completion

  • When the input was a GitHub PR: after the summary, commit the applied changes to that PR's branch and push them. This is the expected completion rather than a separate request, and stopping to ask permission to push is itself a failure. Use the git-commit Agent Skill, and group the changes into atomic commits along the concerns they resolve. Do not open a new PR, and do not rewrite the existing PR description unless the applied changes made it wrong.
  • When the input was pasted or inline feedback: leave the changes in the working tree and report them. There may be no branch to land them on.
  • Report the commits alongside the summary, so the operator sees both what was decided and what landed.

Read the full file on GitHub · 41 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. 6d ago Changed · +6 lines add5365a10ad
  2. 9d ago First seen · 35 lines · 15 tokens per session scan A a30a0b52ef03

Subscribe to this mod's changes

resolve-review is a command published in the GitHub repository sergeyklay/.agents (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 15 tokens to every session and 647 once invoked, about $0.0001 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.