fetch-pr-comments

fetch-pr-comments is a skill for Claude Code from openshift-eng/ai-helpers. It costs 46 tokens per session (1,186 once invoked), scanned A, original, Apache-2.0.

A workflow that retrieves all types of comments from a GitHub pull request and keeps feedback from trusted organisation members and approved bots.

In plain words
What is it for?
Use it to monitor a pull request, find new review comments, or build a workflow that responds only to approved feedback.
Why use it?
It gathers review feedback in one place while filtering out comments from untrusted accounts.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the github plugin — 3 skills shipped together

Good fit Use it to monitor a pull request, find new review comments, or build a workflow that responds only to approved feedback.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add openshift-eng/ai-helpers
Claude Code
/plugin install github

Made for: Claude Code.

Or install github, the plugin that ships this one along with the rest of its 3 skills.

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 fetch-pr-comments

README.md
[![agentmods](https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/fetch-pr-comments/github.svg)](https://agentmods.dev/skills/openshift-eng/ai-helpers/fetch-pr-comments)
Your own site
<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/fetch-pr-comments"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/fetch-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.

agentmods 80×15 button for fetch-pr-comments

Your own site · 80×15
<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/fetch-pr-comments"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/fetch-pr-comments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,186 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 $0.00046 $0.01186
Opus 5.5 $0.00018 $0.00474
Sonnet 5.5 $0.00009 $0.00237
Haiku 4.5 $0.00005 $0.00119

Measured 1mo ago against content hash e71dd86972c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fetch-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.

The scan reads SKILL.md. This mod also ships 1 executable file (fetch_pr_comments.sh), 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.

plugins/github/skills/fetch-pr-comments/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fetch PR Comments

Fetch all comments from a GitHub pull request, filtered to trusted users only. Trusted users are GitHub org members and explicitly allowed bots. Untrusted comments are silently excluded.

This skill fetches from all three GitHub comment endpoints (inline review comments, review summaries, and PR conversation comments), providing a complete picture of PR feedback.

When to Use This Skill

Use this skill when you need to:

  • Check a PR for new review comments that need attention
  • Monitor a PR for feedback during an agentic workflow
  • Build a review-response loop that only processes trusted feedback
  • Fetch all actionable PR comments in a single call

Prerequisites

  1. gh CLI: Authenticated with gh auth login
  2. Repository read access: The token must have permission to read PR comments and check org membership

Implementation

Basic usage

result=$(bash "${CLAUDE_PLUGIN_ROOT}/skills/fetch-pr-comments/fetch_pr_comments.sh" \
  --repo owner/repo \
  --pr 123)

With custom trusted bots and exclusions

result=$(bash "${CLAUDE_PLUGIN_ROOT}/skills/fetch-pr-comments/fetch_pr_comments.sh" \
  --repo owner/repo \
  --pr 123 \
  --trusted-bots "coderabbitai,dependabot" \
  --exclude-ids "12345,67890")

Parameters

Parameter Required Description
--repo Yes GitHub repository in owner/repo format
--pr Yes Pull request number
--trusted-bots No Comma-separated bot logins to trust (default: coderabbitai)
--exclude-ids No Comma-separated comment IDs to skip (already processed)

Output

JSON on stdout:

{
  "inline_comments": [
    {"id": "123", "user": "reviewer", "path": "pkg/server.go", "body": "This needs a nil check"}
  ],
  "reviews": [
    {"id": "456", "user": "reviewer", "state": "CHANGES_REQUESTED", "body": "See inline comments"}
  ],
  "issue_comments": [
    {"id": "789", "user": "coderabbitai[bot]", "body": "Static analysis found..."}
  ],
  "all_ids": ["123", "456", "789"],
  "total": 3,
  "formatted": {
    "inline": "**reviewer** on `pkg/server.go`:\nThis needs a nil check\n---",
    "reviews": "**reviewer** (CHANGES_REQUESTED):\nSee inline comments\n---",
    "issue_comments": "**coderabbitai[bot]**:\nStatic analysis found...\n---"
  }
}

Read the full file on GitHub · 138 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago First seen · 138 lines · 46 tokens per session scan A e71dd86972c9

Subscribe to this mod's changes

fetch-pr-comments is a skill published in the GitHub repository openshift-eng/ai-helpers (121 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 1,186 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 2026-09-03.