A pull-request review command that examines code changes for quality, security, tests, and repository rules. A pull request is a proposed set of changes submitted for review before merging.

Use it to review a diff or changed-file list against a project root. It identifies the project type, applies relevant frontend or backend rules, reports findings by severity, and recommends approval or changes.

It brings several review checks into one report and points to specific files and lines. It also catches changes that leave the allowed project area or violate applicable policies.

pr-reviewer — Command for Claude Code and Cursor by vanessamarely

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.

Clone the repo

git clone --depth 1 https://github.com/vanessamarely/ai-playbook-reposito

Made for: Claude Code, Cursor.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/vanessamarely/ai-playbook-reposito/pr-reviewer/github.svg)](https://agentmods.dev/commands/vanessamarely/ai-playbook-reposito/pr-reviewer)

Your own site

<a href="https://agentmods.dev/commands/vanessamarely/ai-playbook-reposito/pr-reviewer"><img src="https://agentmods.dev/badge/commands/vanessamarely/ai-playbook-reposito/pr-reviewer/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/vanessamarely/ai-playbook-reposito/pr-reviewer"><img src="https://agentmods.dev/badge/commands/vanessamarely/ai-playbook-reposito/pr-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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 729 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00729
Opus 5	$0.00000	$0.00365
Sonnet 5	$0.00000	$0.00146
Haiku 4.5	$0.00000	$0.00073

Measured 12d ago against content hash 6916c585ee13, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pr-reviewer 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 12d 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.

ai-playbook/.cursor/commands/pr-reviewer.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pull Request Reviewer

Analyze pull request changes for quality, security issues, test coverage, and adherence to repository policies (workspace-policy, frontend-policy, backend-policy, style-output rules).

Inputs

diffFile: path to a git diff, or a list of changed files.
projectRoot: root directory of the target project.

Outputs

Review summary with findings categorized by severity.
Inline comments for specific issues (file + line).
Approval or change-request recommendation.

Procedure

Parse the diff — extract modified/added/deleted files, identify file types (source, tests, config, docs), compute scope of change (lines added/removed).
Enforce scope — confirm every changed file stays within projectRoot and doesn't touch sibling projects or excluded directories (node_modules/, dist/, .git/, etc., per workspace-policy). Flag violations.
Detect project type — inspect projectRoot for package.json/tsconfig.json/pom.xml/pyproject.toml to determine applicable policies.
Load relevant policy rules — always apply workspace-policy and style-output; apply frontend-policy for frontend changes and backend-policy for backend changes.
Code quality check per changed source file:
- Style consistency: adherence to project conventions; flag unrelated formatting noise.
- Type safety: any types or missing annotations; unjustified type assertions.
- Error handling: unhandled promise rejections; missing error responses on API endpoints.
- Security: hardcoded secrets/credentials; SQL injection risk (string concatenation in queries); unvalidated user input.
- Performance: inefficient loops/algorithms; synchronous operations in async contexts.
Accessibility check (frontend only) — if frontend files changed, apply the react-components/a11y-automation rules: check for non-semantic interactive elements, missing ARIA labels on icon buttons, missing keyboard handlers.
Test coverage check — confirm tests were added/modified alongside new functionality; flag functionality without corresponding tests. Suggest npm test -- --coverage or the project equivalent.
AI tool instruction check — if the PR touches playbook rules/commands/policies, confirm .cursor/rules/*.mdc, .cursor/commands/*.md, CLAUDE.md, .github/copilot-instructions.md, and AGENTS.md stay consistent with any routing changes. Suggest running /ai-tool-setup if instructions look stale.
Documentation check — public API changes have updated docs/comments; breaking changes include migration notes.
Summarize findings by severity:
- Blocking: security vulnerabilities, breaking changes with no migration path, scope violations.
- Required: missing tests, accessibility violations, type-safety issues.
- Recommended: style/performance improvements, doc gaps, stale AI tool config.
- Nitpick: minor style/naming suggestions.
Generate the review — summary metrics (files changed, lines added/removed), findings by category, inline file:line comments, overall recommendation (Approve / Request Changes / Comment).

Read the full file on GitHub · 44 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.

12d ago First seen · 44 lines · 0 tokens per session scan A 6916c585ee13

Subscribe to this mod's changes

pr-reviewer is a command published in the GitHub repository vanessamarely/ai-playbook-reposito (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 729 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.

Code review Security

pr-reviewer

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Pull Request Reviewer

Inputs

Outputs

Procedure

What this file has done since we first saw it

Other commands, from other repositories

sdd-init

review-branch

init

merge-conflict-analysis

repo-audit

argos