pr-comment

A pull-request review assistant for deciding how to respond to a reviewer's comment: implement it, skip it, ask for clarification, or propose an alternative. A pull request is a proposed code change awaiting review.

In plain words
What is it for?
Use it to investigate review feedback, compare related code, and choose a reasoned response before editing the implementation.
Why use it?
It prevents blindly changing code just to satisfy a review comment. It checks whether the concern is valid and necessary in the current codebase.

Command for Cursor

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/codeready-toolchain/tarsy/pr-comment
Clone the repo
git clone --depth 1 https://github.com/codeready-toolchain/tarsy

Made for: Cursor.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,568 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01568
Opus 5 $0.00000 $0.00784
Sonnet 5 $0.00000 $0.00314
Haiku 4.5 $0.00000 $0.00157

Measured 3d ago against content hash 8aee0b8baa81, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-comment 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 3d 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.

.cursor/commands/pr-comment.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pull Request Review Comment - Context

The user's message contains a Pull Request review comment that needs to be addressed.

Treat the user's input as the reviewer's feedback. Your job is to decide whether to Implement, Skip, Clarify, or Alternative — not to make the review green by default.


How to Address the PR Comment

Follow this systematic approach:

1. Identify the Context

First, determine what code the comment refers to:

  • Read the files mentioned or implied by the comment
  • Use recently viewed files, or file context to identify relevant files
  • Understand the current implementation before proceeding
  • Check how sibling code handles the same concern (other tools, callers, established patterns in this repo). Inconsistency is a signal the suggestion may be over-scoped.

2. Analysis Phase

Do not blindly implement the suggestion. Analyze before writing code.

Soundness vs necessity

A comment can be technically correct and still not worth doing. Judge both:

Question Ask
Sound? Is the finding still true against current code? Is the reviewer mistaken or missing context?
Necessary? What concrete scenario does this prevent or improve? How likely is it here?
Proportionate? Does the added complexity/cost match the realistic risk or benefit?
Consistent? Do peer paths (similar tools/APIs) already accept the same tradeoff?

"Still valid" means still true in the code — not "must implement." Valid but unnecessary nits (theoretical TOCTOU, speculative caching, style-only refactors with large blast radius) should use Skip (disagreement is a common rationale) unless the user explicitly wants them.

Before implementing security, concurrency, or perf nits

State in your reasoning (and to the user if you will change code):

  1. Scenario — the relevant concrete case: failure mode, abuse path, or performance impact (actors, timing/preconditions, and what goes wrong)
  2. Likelihood — why it would or would not happen in this product/path
  3. Decision — exactly one of: Implement / Skip / Clarify / Alternative

Read the full file on GitHub · 170 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. 3d ago First seen · 170 lines · 0 tokens per session scan A 8aee0b8baa81

Subscribe to this mod's changes

pr-comment is a command published in the GitHub repository codeready-toolchain/tarsy (10 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,568 tokens. 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 2026-08-31.