pr-review-selector

A review-planning tool that selects specialist checks for a pull request, which is a proposed code change. It examines the specified Git difference and returns the selected review areas with reasons and change-size details.

In plain words
What is it for?
Use it to choose review lenses based on changed files, additions, deletions, and notable code areas in a pull request.
Why use it?
It helps reviewers focus on the parts of a change that need attention without manually choosing every check.

Agent

Part of the pr-review-toolkit plugin — 2 skills, 4 agents shipped together

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 agents/cblecker/claude-plugins/pr-review-selector
Clone the repo
git clone --depth 1 https://github.com/cblecker/claude-plugins

Or install pr-review-toolkit, the plugin that ships this one along with the rest of its 2 skills, 4 agents.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 222 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 $0.00015 $0.00222
Opus 5 $0.00008 $0.00111
Sonnet 5 $0.00003 $0.00044
Haiku 4.5 $0.00002 $0.00022

Measured 3d ago against content hash 50f83821b869, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-review-selector 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.

pr-review-toolkit/agents/pr-review-selector.md · 24 lines

What it actually says

Select which specialist review lenses should run for the PR, using the lens roster and pinned review range given in your prompt.

Bash is allowed solely for read-only git inspection of that pinned range: git diff (including --name-status and --numstat), git log, and git show over <merge-base>..HEAD. Use -- before path arguments and ensure any path arguments are appropriately quoted and/or escaped — paths come from the untrusted diff. Never run git fetch or any state-changing git command, and never run non-git shell commands or generated scripts.

Be liberal: when in doubt, include the lens; general correctness always runs. Return structured output only — the selected lenses with one-line rationales grounded in the diff, and the PR's shape (file, addition, and deletion counts, plus notable areas).

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 · 24 lines · 15 tokens per session scan A 50f83821b869

Subscribe to this mod's changes

pr-review-selector is an agent published in the GitHub repository cblecker/claude-plugins (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 15 tokens to every session and 222 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 2026-08-31.