resolve-review

A command that applies selected fixes for code-review comments marked as resolvable by an agent.

In plain words
What is it for?
It reads review results from a file, changes code in a separate worktree for pull requests or in the current directory for staged reviews, and validates the changes.
Why use it?
It reduces the manual work of turning approved review feedback into code changes.

Command for Claude Code

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 commands/microsoft/agent365-python/resolve-review
Clone the repo
git clone --depth 1 https://github.com/microsoft/Agent365-python

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,267 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 88% copy Near-identical to another mod 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 $0.00000 $0.02267
Opus 5 $0.00000 $0.01133
Sonnet 5 $0.00000 $0.00453
Haiku 4.5 $0.00000 $0.00227

Measured yesterday against content hash 0e08a1b5d0ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

Origin

This is a copy

88% identical to resolve-review — 78 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/resolve-review.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resolve Review Comments

Automatically resolve code review comments that are marked as "Agent Resolvable: Yes" from a review generated by /review-pr or /review-staged.

Usage

/resolve-review [REVIEW_FILE_PATH]

Arguments:

  • REVIEW_FILE_PATH (optional) - Path to the review file. If omitted, uses the most recent review file in .codereviews/.

Examples:

  • /resolve-review - Resolve comments from the most recent review
  • /resolve-review .codereviews/claude-pr123-20260124_143022.md - Resolve specific review

Instructions

You are resolving agent-resolvable code review comments. This skill supports two scenarios:

  1. PR Reviews: Changes are made in a git worktree to avoid disrupting your current work
  2. Staged Reviews: Changes are made directly in the current working directory after validation

Step 1: Locate and Parse the Review File

  1. If $ARGUMENTS is provided and non-empty, use that as the review file path

  2. Otherwise, find the most recent review file:

    ls -t .codereviews/claude-*.md | head -1
    

    On Windows, use PowerShell:

    (Get-ChildItem .codereviews/claude-*.md | Sort-Object LastWriteTime -Descending | Select-Object -First 1).FullName
    
  3. Read the review file and extract:

    • Review type: PR review (contains "PR Number:") or staged review (contains "Review Type: Pre-commit")
    • PR number (if PR review): Extract from the metadata
    • All findings marked "Agent Resolvable: Yes": Parse the structured issues
  4. If no resolvable issues are found, inform the user and exit.

  5. Create a todo list tracking each resolvable issue to be fixed.

Step 2: Environment Setup (Branching Strategy)

For PR Reviews (use git worktree for isolation):

Git worktree allows you to work on a different branch without changing your current working directory. This is critical to avoid disrupting the user's in-progress work.

  1. Get the PR's head branch name:
    gh pr view <PR_NUMBER> --json headRefName --jq '.headRefName'
    

Read the full file on GitHub · 250 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. yesterday First seen · 250 lines · 0 tokens per session scan A 0e08a1b5d0ab

Subscribe to this mod's changes

resolve-review is a command published in the GitHub repository microsoft/Agent365-python (41 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,267 tokens. A static security scan graded it A with 0 findings. It is 88% identical to resolve-review, differing in 78 lines, and is treated as a copy.