gh-address-comments

gh-address-comments is a skill for Claude Code, Codex from jmagar/claude-homelab. It costs 85 tokens per session (1,420 once invoked), scanned A, original, MIT.

A workflow for handling review comments on GitHub pull requests, which are proposed code changes reviewed before merging. It tracks each comment and checks that every one is resolved.

In plain words
What is it for?
Use it to find the current branch’s pull request, work through reviewer comments, connect fixes to specific reviews, and verify that no review threads are unresolved.
Why use it?
It prevents review feedback from being missed or a pull request being treated as finished while comments remain open.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the homelab-core plugin — 18 skills, 5 commands, 1 agent shipped together

Good fit Use it to find the current branch’s pull request, work through reviewer comments, connect fixes to specific reviews, and verify that no review threads are unresolved.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jmagar/claude-homelab/gh-address-comments
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 jmagar/claude-homelab --skill gh-address-comments
Clone the repo
git clone --depth 1 https://github.com/jmagar/claude-homelab

Made for: Claude Code, Codex.

Or install homelab-core, the plugin that ships this one along with the rest of its 18 skills, 5 commands, 1 agent.

Its marketplace also offers this one on its own, as the plugin gh-address-comments/plugin install gh-address-comments after adding the marketplace above.

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 gh-address-comments

README.md
[![agentmods](https://agentmods.dev/badge/skills/jmagar/claude-homelab/gh-address-comments/github.svg)](https://agentmods.dev/skills/jmagar/claude-homelab/gh-address-comments)
Your own site
<a href="https://agentmods.dev/skills/jmagar/claude-homelab/gh-address-comments"><img src="https://agentmods.dev/badge/skills/jmagar/claude-homelab/gh-address-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.

agentmods 80×15 button for gh-address-comments

Your own site · 80×15
<a href="https://agentmods.dev/skills/jmagar/claude-homelab/gh-address-comments"><img src="https://agentmods.dev/badge/skills/jmagar/claude-homelab/gh-address-comments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,420 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00085 $0.01420
Opus 5 $0.00043 $0.00710
Sonnet 5 $0.00017 $0.00284
Haiku 4.5 $0.00009 $0.00142

Measured 12d ago against content hash a5a3dd04767d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

gh-address-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 12d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (examples/basic-workflow.sh, load-env.sh, scripts/fetch_comments.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/gh-address-comments/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Comment Handler with Resolution Tracking

⚠️ MANDATORY SKILL INVOCATION ⚠️

YOU MUST invoke this skill (NOT optional) when the user mentions ANY of these triggers:

  • "address PR comments", "fix review feedback", "handle PR review"
  • "resolve PR threads", "respond to review", "work through comments"
  • "address the feedback", "mark threads resolved", "clear review comments"
  • Any mention of systematically handling GitHub pull request review comments

Failure to invoke this skill when triggers occur violates your operational requirements.

Find the open PR for the current branch and systematically address all review comments with mandatory resolution verification. This workflow ensures no feedback slips through the cracks by tracking threads as tasks, linking commits to specific reviews, and blocking completion if any threads remain unresolved. Run all gh commands with elevated network access.

Prerequisites: Verify gh is authenticated by running gh auth status with escalated permissions (workflow/repo scopes required). If not authenticated, run gh auth login --scopes repo,workflow. If sandboxing blocks gh auth status, rerun with sandbox_permissions=require_escalated.

Workflow

1) Fetch all PR comments

Run python3 $HOME/.claude/skills/gh-address-comments/scripts/fetch_comments.py to fetch all comments and review threads on the PR. Store output for later verification.

Example:

python3 $HOME/.claude/skills/gh-address-comments/scripts/fetch_comments.py > /tmp/pr_comments.json

2) Create tracking checklist

Parse the fetched comments and create a task checklist using TaskCreate for each review thread. Each task should:

  • Include the thread number, file path, line number, and comment summary
  • Have status pending initially
  • Store the thread ID in task metadata for later resolution

Task format:

  • Subject: Address comment #N: [file]:[line]
  • Description: Comment author, body preview, and what needs to be done
  • Metadata: {"thread_id": "PRRT_kwDOABC...", "file": "path/to/file.ts", "line": 42}

Read the full file on GitHub · 143 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. 12d ago First seen · 143 lines · 85 tokens per session scan A a5a3dd04767d

Subscribe to this mod's changes

gh-address-comments is a skill published in the GitHub repository jmagar/claude-homelab (78 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 1,420 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

pr-generator

Use this skill when creating a pull request — generate the title, structured description, and review checklist from the branch's actual commits and diff. Don't use it for commit messages (git-commit skill) or changelogs.

atretyak1985/swarmery · 48 tokens

hunk-extensions

Maps the hunkdiff/extension authoring surface for Hunk, the terminal diff viewer — hiding or reordering reviewed files, docked panes, alternate file views, commands and key bindings, dialogs, workspace writes, themes, syntax languages, VCS backends, lifecycle events. Use when writing, debugging, or installing a Hunk…

modem-dev/hunk · 105 tokens

hunk-launch-video

Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.

modem-dev/hunk · 60 tokens

hunk-release

Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.

modem-dev/hunk · 38 tokens

hunk-review

Interacts with live Hunk diff review sessions via CLI. Inspects review focus, navigates files, hunks, and exact lines, reloads session contents, adds inline review comments, and paints attention marks on character ranges. Use when the user has a Hunk session running or wants to review diffs interactively.

modem-dev/hunk · 69 tokens

pr-review

Review open PRs two ways - default is a per-PR deep review with severity-tagged findings, inline comments, and a verdict; --survey runs a risk-tiered triage digest of what's safe to merge first.

aeonfun/aeon · 47 tokens