handle-pr-reviewer-feedback

handle-pr-reviewer-feedback is a skill for Claude Code from tomzx/agents. It costs 39 tokens per session (1,138 once invoked), scanned A, original, MIT.

A workflow for handling review comments on a pull request you created. A pull request is a proposed code change submitted for review on GitHub.

In plain words
What is it for?
It helps update code in response to review, explain why some suggestions are not accepted, and optionally commit, push, or post replies to GitHub.
Why use it?
It gathers reviewer feedback in one process, separates valid requests from rejected suggestions, and reduces the chance of leaving comments unanswered.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Good fit It helps update code in response to review, explain why some suggestions are not accepted, and optionally commit, push, or post replies to GitHub.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomzx/agents/handle-pr-reviewer-feedback
View source ↗ tomzx/agents
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.

Any agent
npx skills add tomzx/agents --skill handle-pr-reviewer-feedback
Clone the repo
git clone --depth 1 https://github.com/tomzx/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 handle-pr-reviewer-feedback

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomzx/agents/handle-pr-reviewer-feedback/github.svg)](https://agentmods.dev/skills/tomzx/agents/handle-pr-reviewer-feedback)
Your own site
<a href="https://agentmods.dev/skills/tomzx/agents/handle-pr-reviewer-feedback"><img src="https://agentmods.dev/badge/skills/tomzx/agents/handle-pr-reviewer-feedback/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 handle-pr-reviewer-feedback

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomzx/agents/handle-pr-reviewer-feedback"><img src="https://agentmods.dev/badge/skills/tomzx/agents/handle-pr-reviewer-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,138 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 $0.00039 $0.01138
Opus 5 $0.00019 $0.00569
Sonnet 5 $0.00008 $0.00228
Haiku 4.5 $0.00004 $0.00114

Measured 6d ago against content hash eb70d415c8e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

handle-pr-reviewer-feedback 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.

skills/handle-pr-reviewer-feedback/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handle PR Reviewer Feedback

Reviews and responds to all reviewer comments on a GitHub pull request you authored, implementing valid feedback or explaining rejections with clear justification. On user approval it commits and pushes changes; whether replies are posted to GitHub is decided by should-post-to-github (based on ~/.sdlc/config.yaml), otherwise replies are drafted without posting.

For the reviewer-side flow (verifying that a PR author addressed your review comments), use handle-pr-author-feedback instead.

Prerequisites

  • Apply the shared SDLC conventions in skills/sdlc/references/shared.md.
  • If no argument is provided, target the pull request from $PR_NUMBER (and $REPO).
  • gh CLI authenticated with write access to the target repository
  • PR number identifying an open pull request with at least one review comment
    • If $1 is provided, use it directly
    • If $1 is not provided, resolve the PR number with: gh pr list --head $(git branch --show-current) --json number --jq '.[0].number'

Skill attribution (GitHub)

Before posting any PR comment with gh, read github-post-attribution/SKILL.md and append the Posted with footer for SKILL_DIR = handle-pr-reviewer-feedback.

Workflow

Fetch PR comments ($1)
        |
        v
  For each comment
        |
        v
  Evaluate: actionable or not?
        |
        v
   Present outcome to user for approval
      /         \
  Approved     Rejected
     |             |
     v             v
  Implement       Skip
  changes
      |
      v
  Commit + push
  (always on approval)
      |
      v
     Reply to each comment thread
     with outcome (ghx), only if
     should-post-to-github allows

Steps

  1. Fetch all PR review threads:
    ghx pr threads $1 --ids
    
  2. For each comment, evaluate whether it is appropriate and actionable.
  3. Present the evaluation and proposed action (implement or reject with explanation) to the user for approval.
  4. For actionable comments that the user approved: implement the requested changes in the codebase.
  5. Commit and push the changes (push is not gated):
    git add -A && git commit -m "<message>"
    git push
    
  6. Decide whether to post replies: get the PR author (gh pr view $1 --repo <owner>/<repo> --json author --jq .author.login), then run ~/.agents/scripts/should-post-to-github --repo "<owner>/<repo>" --author "<PR_AUTHOR>". If it exits 0, reply to each comment thread with the outcome using ghx. For actionable comments where changes were implemented: reply with a brief summary and a link to the commit (e.g., "Done: added null guard for user in abc1234."). For non-actionable comments: reply with the rejection explanation. Use the thread IDs from step 1:
    ghx pr comment $1 --reply-thread <thread-id> --body "<outcome summary>"
    
    Append the Skill attribution footer to each reply. If the script exits 1, present the drafted replies to the user without posting.

Read the full file on GitHub · 108 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 First seen · 108 lines · 39 tokens per session scan A eb70d415c8e9

Subscribe to this mod's changes

handle-pr-reviewer-feedback is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 1,138 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 2026-09-03.