thepopebot: Command for Claude Code

.claude/commands/review-issue.md

review-issue is a command for Claude Code from stephengpope/thepopebot. It costs 17 tokens per session (520 once invoked), scanned A, original, MIT.

A review guide for analyzing a GitHub issue or pull request and producing an implementation plan without changing the code or repository.

In plain words
What is it for?
Use it to review an issue or pull request before implementation. It identifies the request type, checks required details, asks for missing information when needed, and then guides code analysis and planning.
Why use it?
It checks whether bug reports and feature requests contain the information needed for reliable planning. It prevents analysis from starting when key details, such as platform or reproduction steps, are missing.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is stephengpope/thepopebot's own configuration. It tells Claude Code how to work on thepopebot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything thepopebot configures →

About the project

The Pope Bot is an app for configuring an autonomous AI agent that can chat, run coding work, and operate continuously through connected language models and coding agents. People use it for questions, code changes, background development jobs, and live browser-based coding sessions. Its catalogue add-ons extend the bot with commands, skills, and operating instructions.

stephengpope/thepopebot · 1,860 stars · on GitHub · skool.com

Reuse

Borrowing it

Nothing to install: this file belongs to stephengpope/thepopebot. 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/stephengpope/thepopebot/main/.claude/commands/review-issue.md
Clone the repo
git clone --depth 1 https://github.com/stephengpope/thepopebot

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 review-issue

README.md
[![agentmods](https://agentmods.dev/badge/commands/stephengpope/thepopebot/review-issue/github.svg)](https://agentmods.dev/commands/stephengpope/thepopebot/review-issue)
Your own site
<a href="https://agentmods.dev/commands/stephengpope/thepopebot/review-issue"><img src="https://agentmods.dev/badge/commands/stephengpope/thepopebot/review-issue/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 review-issue

Your own site · 80×15
<a href="https://agentmods.dev/commands/stephengpope/thepopebot/review-issue"><img src="https://agentmods.dev/badge/commands/stephengpope/thepopebot/review-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 520 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 $0.00017 $0.00520
Opus 5 $0.00009 $0.00260
Sonnet 5 $0.00003 $0.00104
Haiku 4.5 $0.00002 $0.00052

Measured 9d ago against content hash 8ac4fd40e61d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-issue 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 9d 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/commands/review-issue.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DO NOT implement any changes. DO NOT create branches, commits, or PRs. You can only read code and produce a plan or ask questions.

You are a senior software architect reviewing an issue/PR thread.

Step 1 — Identify Issue Type and Check for Required Information

First, determine the issue type from labels or content:

Bug Reports (label: bug)

Check that the issue includes:

  • NPM Version (thepopebot version from package.json or npm list)
  • Platform (macOS, Linux, or Windows)
  • Description (what happened, what they expected)
  • Steps to Reproduce (minimal repro steps)

Feature Requests (label: enhancement)

Check that the issue includes:

  • Description (what feature they want)
  • Use Case (why they need it, what problem it solves)

If required information is missing:

  • Tag the issue author (e.g., @username) and ask for the specific missing details
  • List exactly what you need in a numbered list
  • Do NOT proceed with a plan until you have enough information
  • STOP here — do not analyze the codebase yet

Skip this check only if the request is dead obvious (typo fix, trivial change).

Step 2 — Analyze and Plan

Once you have sufficient information:

  1. Read the ENTIRE thread — the original description and every comment
  2. Identify the core requirements, constraints, and any decisions already made
  3. Cross-reference against the actual codebase to understand current state
  4. Then do ONE of the following:

Option A — Requirements are clear

Post a structured implementation plan:

  • Summary: One paragraph describing the change
  • Files to modify/create: List each file path with a bullet describing changes
  • Implementation steps: Numbered, in dependency order
  • Testing strategy: What tests to add or update
  • Risks & edge cases: Anything that could go wrong
  • Open questions: Minor uncertainties (if any)

Option B — Requirements are unclear

Ask specific, numbered clarifying questions. For each question, explain WHY you need the answer and what decision it affects. Tag the relevant person so they get notified.

Read the full file on GitHub · 64 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. 9d ago First seen · 64 lines · 17 tokens per session scan A 8ac4fd40e61d

Subscribe to this mod's changes

review-issue is a command published in the GitHub repository stephengpope/thepopebot (1,860 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 520 once invoked, about $0.0001 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.