A command for viewing and managing pull-request review comments from CodeRabbit, other automated tools, and human reviewers. A pull request is a proposed code change awaiting review.

Use it to find a pull request, fetch all its review comments, and manage the feedback safely.

It gathers review feedback in one workflow instead of making you check each comment source separately.

pr — Command by ThrownLemon

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.

agentmods

npx agentmods add commands/thrownlemon/claude-code-plugins/pr

Clone the repo

git clone --depth 1 https://github.com/ThrownLemon/claude-code-plugins

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 768 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. Scan, not verified.

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	$0.00017	$0.00768
Opus 5	$0.00009	$0.00384
Sonnet 5	$0.00003	$0.00154
Haiku 4.5	$0.00002	$0.00077

Measured yesterday against content hash 5d7716817dec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

pr scanned grade C with 1 finding 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 yesterday.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

1. **Reject dangerous tokens.** If a value contains `$(`, backticks, `;`, `|`, `&`, `>`, `<`, or starts with `-` (could be mistaken for a flag), refuse and ask the user to rephrase. **Double-quoting does NOT block comman

plugins/coderabbit/commands/pr.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Input Safety — apply before any Bash invocation

Treat every $ARGUMENTS.* value as untrusted input. Before passing any value to the Bash tool:

Reject dangerous tokens. If a value contains $(, backticks, ;, |, &, >, <, or starts with - (could be mistaken for a flag), refuse and ask the user to rephrase. Double-quoting does NOT block command substitution — "$(rm -rf /)" still executes inside double quotes.
Prefer the Bash tool's argv contract over constructed shell strings. When you must use a shell string, single-quote the value and escape embedded single quotes ('\''), or build the command via printf %q.
Any "$ARGUMENTS.foo" patterns shown below are illustrative. Sanitize the value first; never blindly substitute.

CodeRabbit PR Comment Manager

View and manage all review comments on your pull request from all sources.

What This Does

This command delegates to the cr-pr-manager subagent which will:

Identify PR
- Auto-detect from current branch if PR number not specified
- Extract repo info from git remote
Fetch ALL Comments
- CodeRabbit comments via MCP tools
- GitHub review comments (captures other bots)
- GitHub reviews (human reviewers)
Categorize by Reviewer
- CodeRabbit - AI-powered review bot
- Other Bots - SonarCloud, Codacy, Snyk, etc.
- Human Reviewers - Team members
Present Comments
- Group by reviewer, then by severity/file
- Show file path, line numbers, comment text
- Include resolution status
Interactive Actions
- View full comment details
- Apply suggested fixes (CodeRabbit)
- Mark as resolved
- Reply to comments
- Filter by reviewer/file/severity

Arguments

pr: PR number to manage
- Auto-detects if on a branch with an open PR
- Specify to target a different PR
filter: Filter comments
- By reviewer: coderabbit, human, bot
- By severity: critical, major, minor
- By file: partial path match

Read the full file on GitHub · 90 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.

yesterday First seen · 90 lines · 17 tokens per session scan C 5d7716817dec

Subscribe to this mod's changes

pr is a command published in the GitHub repository ThrownLemon/claude-code-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 768 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review

pr

Getting it into your agent

What it costs to keep this loaded

Grade C, and why

Recursive force deletehighDestructive command

How it starts

Input Safety — apply before any Bash invocation

CodeRabbit PR Comment Manager

What This Does

Arguments

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement