What is address-pr-comments?

A pull request review helper that reads every review comment, applies agreed fixes, and prepares replies. A pull request is a proposed code change awaiting review; it groups discussion and changes in one place.

Use it to process inline comments, review summaries, and general discussion on a pull request, then make fixes and create separate commits.

It prevents comments from being missed and keeps fixes organised by area. It also links replies to the commits that address them, while asking before pushing changes.

How banshee-data/velocity.report configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to banshee-data/velocity.report. 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/banshee-data/velocity.report/main/.claude/skills/address-pr-comments/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/banshee-data/velocity.report

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/banshee-data/velocity.report/address-pr-comments/github.svg)](https://agentmods.dev/skills/banshee-data/velocity.report/address-pr-comments)

Your own site

<a href="https://agentmods.dev/skills/banshee-data/velocity.report/address-pr-comments"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/address-pr-comments/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/banshee-data/velocity.report/address-pr-comments"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/address-pr-comments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,099 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.

Model	Per session	Once invoked
Fable 5.1	$0.00042	$0.02099
Opus 5.5	$0.00017	$0.00840
Sonnet 5.5	$0.00008	$0.00420
Haiku 4.5	$0.00004	$0.00210

Measured 1mo ago against content hash 7347e018ac9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

address-pr-comments 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.

.claude/skills/address-pr-comments/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: address-pr-comments

Walk through every open review comment on a PR, decide which ones are actionable, apply fixes, commit the work split by area, and reply to each thread referencing the commit SHA that resolves it.

Usage

/address-pr-comments
/address-pr-comments 473
/address-pr-comments feature/lidar-l7-scene

If no argument is given, use the current branch and find its open PR.

Procedure

1. Identify the PR

If a PR number is given, use it directly. Otherwise:

git branch --show-current
gh pr view --json number,title,state,headRefName,baseRefName

If no open PR exists, stop and tell the operator.

2. Collect all comments

There are three comment surfaces on a PR and they live in different endpoints. Fetch all of them:

# Inline review comments (attached to code lines)
gh api repos/{owner}/{repo}/pulls/{number}/comments --paginate

# Review summary comments (the top-level body of each review)
gh api repos/{owner}/{repo}/pulls/{number}/reviews --paginate

# Issue-style comments (general PR conversation, not attached to code)
gh api repos/{owner}/{repo}/issues/{number}/comments --paginate

For each comment record keep: id, user.login, path, line, body, in_reply_to_id, pull_request_review_id.

Filter out:

Your own prior replies (same bot/user that would be posting)
Threads that already have a reply from the PR author accepting or rejecting the point (look for in_reply_to_id chains)
Outdated comments (the API marks these with position: null)

Group remaining comments into threads by in_reply_to_id so each thread is addressed once.

3. Triage each comment

For every live thread, classify it:

Class	Meaning	Action
actionable	Clear code change requested, you understand what to do	Fix it
disagree	Reviewer is wrong (misreads the diff, contradicts project convention)	Reply only, no code change
ambiguous	Valid point but several ways to fix, or you aren't sure what is meant	Ask the operator before proceeding
out-of-scope	Valid but belongs in a follow-up PR	Reply acknowledging + link to backlog entry, no code change in this PR
nit	Style preference the reviewer flagged as non-blocking	Fix if trivial, else reply and skip

Read the full file on GitHub · 228 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.

1mo ago First seen · 228 lines · 42 tokens per session scan A 7347e018ac9c

Subscribe to this mod's changes

address-pr-comments is a skill published in the GitHub repository banshee-data/velocity.report (11 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 2,099 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 2026-09-25.

Code review Commits Git and workflow lidar radar road-safety street-safety traffic-analysis urban-analytics

address-pr-comments next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
address-pr-commentsbanshee-data/velocity.report	Skill	11	today	Apache-2.0	A	42	Claude Code
review-implement-phaseprisma/orm	Skill	48k	yesterday	Apache-2.0	A	38	Claude Code
github-pr-workflowpaperclipai/paperclip	Skill	111k	yesterday	MIT	A	39	Claude Code, Codex
review-deltatirth8205/code-review-graph	Skill	33k	8d ago	MIT	A	24	Claude Code
hero-diff-highlightUnclecheng-li/AI_Animation	Skill	1.7k	11d ago	MIT	A	0	Claude Code, Codex
lean-reviewSnowflake-Labs/cocoplus	Skill	727	2d ago	MIT	A	44	Claude Code
git-pr-workflows-git-workflowrmyndharis/antigravity-skills	Skill	1.9k	23d ago	MIT	A	37	Claude Code

velocity.report: Skill for Claude Code